The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index; 13 of the 40 sources its claims cite were checked for support.
Simple techniques to bypass GenAI text detectors: implications for inclusive education
Open accessPublished version of a preprint
Abstract
This study investigates the efficacy of six major Generative AI (GenAI) text detectors when confronted with machine-generated content modified to evade detection (n = 805). We compare these detectors to assess their reliability in identifying AI-generated text in educational settings, where they are increasingly used to address academic integrity concerns. Results show significant reductions in detector accuracy (17.4%) when faced with simple techniques to manipulate the AI generated content. The varying performances of GenAI tools and detectors indicate they cannot currently be recommended for determining academic integrity violations due to accuracy limitations and the potential for false accusation which undermines inclusive and fair assessment practices. However, these tools may support learning and academic integrity when used non-punitively. This study aims to guide educators and institutions in the critical implementation of AI text detectors in higher education, highlighting the importance of exploring alternatives to maintain inclusivity in the face of emerging technologies.
Overview
CoChat Summary
TL;DR
This experimental study tested seven AI text detectors on 114 samples, including 15 AI-generated texts, 89 adversarially modified AI texts, and 10 human controls. The detectors performed poorly overall and became substantially less accurate after simple adversarial techniques, raising concerns about fairness, false accusations, and the use of such tools in inclusive educational assessment.
Key findings
- Across unmanipulated AI-generated content, the mean detector accuracy was 39.5%; for human-written control samples, accuracy was 67%.
- After adversarial techniques were applied, mean detector accuracy fell to 22.14%; the paper also reports an overall 17.4% mean drop in accuracy.
- Some techniques were especially effective: adding spelling errors and increasing burstiness were described as highly effective, with manipulated-output accuracies of 12.9% and 15.9%, respectively; increase complexity had only a 2% drop in detectability and was the least effective.
- Detector performance varied widely: Copyleaks was the most accurate at 73.9% on non-manipulated output and 58.7% on manipulated output, while GPT Kit was the least accurate at 6% and 4.5%, respectively; Turnitin had the largest accuracy drop at 42.1%.
- Error analysis found that four of seven detectors did not misclassify any human-written samples, but Copyleaks misidentified 50% of human samples as AI-written; for undetected machine-generated cases, six of seven detectors had a UDC ratio above 50%, and Copyleaks still failed to identify 39% of AI-generated cases.
Methods
- Experimental design using three GenAI tools (GPT-4, Claude 2, Bard) to create 15 short text samples from five standardized prompts; those samples were then modified with six adversarial techniques to produce 89 additional AI-generated samples, alongside 10 human-written controls.
- All 114 samples were tested against seven AI text detectors: Turnitin, GPTZero, ZeroGPT, Copyleaks, Crossplag, GPT-2 Output Detector, and GPTKit; there were 805 tests in total and 797 valid tests.
- Accuracy was calculated using three methods—binary, semi-binary, and logarithmic—and the paper also conducted error analysis for false accusations and undetected cases.
Limitations
- The paper explicitly states that the study used a relatively small number of samples, only three GenAI tools and seven detectors, so the findings do not cover the full range of possible tools, styles, or manipulations.
- The authors say the results are only a snapshot in time because both GenAI tools and detectors evolve quickly; they may not remain stable for long.
- The paper notes that 8 samples could not be tested with some tools because of proprietary software issues; it also says some failures may have been due to text length limits, formatting incompatibilities, or temporary server issues.
- Evident from the design: the study used short, controlled samples and did not mirror the iterative real-world writing/editing process, which the authors say may mean real-world detectability could be even lower.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 Valid · 2 Not valid · 20 Not checked · 91 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Mitchell et al. (2023) identified that DetectGPT correctly detected 70.3% of model-generated sequences from GPT2-XL.”
What the sources say
- Partly supportedcites Mitchell et al. (2023) sourceExperimental — accuracy not yet measured
Table 1 reports that DetectGPT detects GPT-2-generated samples, but its results are AUROC values, not the percentage of generated sequences correctly detected. The cited paper’s results do not substantiate the specific 70.3% figure. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“These include 'recursive paraphrasing attacks' , which utilise automated, network-based paraphrasing tools to reduce the accuracy of detectors on watermarked texts”
What the sources say
- Could not verifycites Solaiman et al. (2019) sourceExperimental — accuracy not yet measured
The paper’s ‘4.3 Detecting Synthetic Text’ section discusses adversaries using better generation systems to challenge detectors, but does not address recursive paraphrasing attacks. Searches for recursive paraphrasing and for watermark-related detector accuracy found no passage about automated paraphrasing tools reducing detection accuracy on watermarked text. (LLM, conf=0.73)
- Supportedcites Sadasivan et al. (2023) source
The Introduction (p. 3) describes an automated recursive attack using neural network-based paraphrasing and reports that it lowers detection rates for watermarked text. Section 2.3 (p. 7) likewise reports that repeated paraphrasing further degrades the watermark detector’s detection rate. (LLM, conf=0.94)
- Not matchedcites Ippolito etal. (2020)
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, claims of accuracy are contradicted by studies which demonstrate the varied levels of the detectors' ability to distinguish accurately between AI and human-generated content. (Chaka, 2023a; Gao etal., 2022; Krishna etal., 2023; Orenstrakh etal., 2023; Perkins etal., 2023; Walters, 2023; Weber-Wulff etal., 2023).”
What the sources say
- Supportedcites Chaka, 2023a source
The Copyleaks AI Content Detector section reports the provider’s claim of 99.12% detection accuracy. The Discussion reports substantially varied results across the five detectors, including misclassifications and a detector that correctly classified only one text; the Implications and limitations section says they could not clearly distinguish AI-generated from human-produced texts. No page numbers are available in our copy. (LLM, conf=0.92)
- Not matchedcites Gao etal., 2022
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Krishna etal., 2023
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, after altering the content using an Automated Paraphrasing tool (APT), the detection rate decreased to 4.6%.”
What the sources say
- Partly supportedcites Mitchell et al. (2023) sourceExperimental — accuracy not yet measured
Section 5.2 reports that detection performance generally declines as machine-generated text is increasingly revised. It simulates revisions by replacing text spans with T5-3B output and reports AUROC, not a detection rate of 4.6% after use of an Automated Paraphrasing Tool. No page number is provided in our copy. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“we noted that AI detectors performed significantly worse in our study, even with unedited text.”
What the sources say
- Supportedcites Weber-Wulff (2023) source
The Variations in accuracy section (p. 16) reports 74% accuracy for AI-generated texts with no further modifications, providing the cited study’s unedited-text benchmark. The statement that detectors performed worse in the citing authors’ own study is their comparison, not a result attributed to Weber-Wulff et al. (LLM, conf=0.87)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
53 more claims · 1 with their cited sources checked
Create a free account to see all 123 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 41
- It may state two separate claims as one. 38
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Studies further illustrate that even minor textual alterations, such as synonym replacement, sentence reconfiguration, or translation cycles, can markedly diminish detection accuracy.”
From Harms and Ethical Risks of AI Detection Tools in Education: False Positives, Bias, Surveillance, and Student Rights (2026) · cites this paper as Perkins et al., 2024
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“However, in the current state, reliable detection procedures are scarce (Elkhatat et al., 2023;Kofinas et al., 2025;Perkins et al., 2024).”
From Policy analysis of higher education institutes in Ontario, Canada: A focus on artificial intelligence (2025) · cites this paper as Perkins et al., 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| Total/Average | 9 | 414 | 15 | 65.7 |”
Reported 414 · recomputed 503
Citations
Cites
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.03109 · Cited by 3,159 · cited 1×
“Despite these achievements, Claude 2 lags in scientific writing and quantitative accuracy compared to other models (Chang et al., 2023; Lozić & Štular, 2023; Z. Wu et al., 2023), primarily because of the ability of GPT-4 and Bard to access the internet for information gathering.”
MethodChatting and cheating: Ensuring academic integrity in the era of ChatGPT
Cotton, D. R. E., Cotton, P. A., & Shipway, J. R. (2024) · Innovations in Education and Teaching International · doi:10.1080/14703297.2023.2190148 · Cited by 3,087 · cited 1×
“…on problematising text-detection software from a perspective of inclusiv-ity, too much focus on GenAI as an emerging risk to academic integrity (Cotton et al., 2023; Perkins, 2023) may lead us to forget that extant threats to inclusivity and educational equity, such as contract cheating or…”
Chatting and Cheating. Ensuring academic integrity in the era of ChatGPT
Cotton, D., Cotton, P., & Shipway, J. R. (2023) · doi:10.35542/osf.io/mrz8h · Cited by 3,079
A comprehensive AI policy education framework for university teaching and learning
Chan, C. K. Y. (2023) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-023-00408-3 · Cited by 1,577 · cited 1×
“…which accepts the use of GenAI in crafting manuscripts, albeit with certain restrictions (Per-kins & Roe, 2024a), and studies have shown the rising popularity of using GenAI tools to support academic writing and research (Bedington et al., 2024; Chan, 2023; Perkins & Roe, 2024b; Sobaih, 2024).”
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2022) · doi:10.1101/2022.12.23.521610 · Cited by 1,099 · cited 3×
“All samples created were tested against seven AI text detectors which had been previously identified in literature (Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins, Roe, et al., 2023; Weber-Wulff et al., 2023)as being somewhat effective at successfully…”
MethodGao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00819-6 · Cited by 1,099
Perkins, M. (2023) · Journal of University Teaching and Learning Practice · doi:10.53761/1.20.02.07 · Cited by 839
Self-citationCan AI-Generated Text be Reliably Detected?
Sadasivan, V. S., Kumar, A., Balasubramanian, S., Wang, W., & Feizi, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11156 · Cited by 810 · cited 2×
“…evade detection as ‘adversarial techniques’ in reference to the combination of methods that have been referred to as adversarial attacks in the extant literature related to attacks on machine learning based tools (Alsmadi et al., 2021; Qiu et al., 2019; Sadasivan et al., 2023; Wang et al., 2023).”
BackgroundMethodGPT detectors are biased against non-native English writers
Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J. (2023) · Patterns · doi:10.1016/j.patter.2023.100779 · Cited by 673 · cited 8×
“Detection tool biases against NNES have been highlighted as a potential issue of bias by Fröhling and Zubiaga (2021) and Liang et al. (2023) because of their reliance on standardised linguistic metrics such as perplexity and burstiness, which can disadvantage NNES.”
BackgroundInfluentialTesting of detection tools for AI-generated text
Weber-Wulff, D., Anohina-Naumeca, A., Bjelobaba, S., Foltýnek, T., Guerrero-Dib, J., Popoola, O., Šigut, P., & Waddington, L. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00146-z · Cited by 582 · cited 8×
“…were tested against seven AI text detectors which had been previously identified in literature (Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Weber-Wulff et al., 2023) as being somewhat effective at successfully identifying GenAI content.”
InfluentialReview of Artificial Intelligence Adversarial Attack and Defense Technologies
Qiu, S., Liu, Q., Zhou, S., & Wu, C. (2019) · Applied Sciences · doi:10.3390/app9050909 · Cited by 411 · cited 1×
“…evade detection as ‘adversarial techniques’ in reference to the combination of methods that have been referred to as adversarial attacks in the extant literature related to attacks on machine learning based tools (Alsmadi et al., 2021; Qiu et al., 2019; Sadasivan et al., 2023; Wang et al., 2023).”
Digital inequalities in the age of artificial intelligence and big data
Lutz, C. (2019) · Human Behavior and Emerging Technologies · doi:10.1002/hbe2.140 · Cited by 411 · cited 1×
“For instance, students with access to advanced AI tools and knowledge of adversarial techniques could gain an unfair advantage over their peers, further widening extant digital inequalities and the digital divide (Lutz, 2019).”
The manifold costs of being a non-native English speaker in science
Amano, T., Ramírez-Castañeda, V., Berdejo-Espinola, V., Borokini, I., Chowdhury, S., Golivets, M., González-Trujillo, J. D., Montaño-Centellas, F., Paudel, K., White, R. L., et al. (2023) · PLOS Biology · doi:10.1371/journal.pbio.3002184 · Cited by 403 · cited 1×
“These ‘manifold costs’ include spending a greater amount of effort and time reading, writing, and disseminating work (Amano et al., 2023).”
Elkhatat, A. M., Elsaid, K., & Almeer, S. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00140-5 · Cited by 392 · cited 4×
“…to a lack of holistic understanding of the interplay between AI text detectors, GenAI models, and adversarial techniques (Anderson et al., 2023; Chaka, 2023b; Elali & Rachid, 2023; Elkhatat et al., 2023; Liang et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Weber-Wulff et al., 2023).”
InfluentialLin, Y., & Chen, Y.-N. (2023) · Workshop on NLP for Conversational AI (NLP4ConvAI) · doi:10.18653/v1/2023.nlp4convai-1.5 · Cited by 363
Release Strategies and the Social Impacts of Language Models
Solaiman, I., Brundage, M., Clark, J., Askell, A., Herbert-Voss, A., Wu, J., Radford, A., Krueger, G., Kim, J. W., Kreps, S., et al. (2019) · arXiv · doi:10.48550/arxiv.1908.09203 · Cited by 292 · cited 1×
“Other techniques for evading the identification of machine-generated text have also been presented by Solaiman et al. (2019), Sadasivan et al. (2023) and Ippolito et al. (2020).”
MethodPerkins, M., Furze, L., Roe, J., & MacVaugh, J. (2024) · Journal of University Teaching and Learning Practice · doi:10.53761/q3azde36 · Cited by 291 · cited 1×
“…in enhancing academic practices for both students and teachers alike, and most publishing houses now permit the transparent use of such tools (Perkins & Roe, 2024a; STM, 2023), there are circumstances in which the detection of GenAI texts remains necessary, such as in assessment practices…”
Self-citationAutomatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2019) · arXiv · doi:10.48550/arxiv.1911.00650 · Cited by 264 · cited 1×
“Other techniques for evading the identification of machine-generated text have also been presented by Solaiman et al. (2019), Sadasivan et al. (2023) and Ippolito et al. (2020).”
MethodAutomatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264
Perkins, M., Roe, J., Postma, D., McGaughran, J., & Hickerson, D. (2024) · Journal of Academic Ethics · doi:10.1007/s10805-023-09492-6 · Cited by 234 · cited 8×
“…model represented a step-change in the abilities of GenAI to create text that was significantly more difficult to detect by educators (Fleckenstein et al., 2024; Perkins et al., 2023), and thus the technology began to draw greater attention in the public sphere, as well as in educational contexts.”
InfluentialSelf-citationTowards a Robust Deep Neural Network against Adversarial Texts: A Survey
Wang, W., Wang, R., Wang, L., Wang, Z., & Ye, A. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3117608 · Cited by 198 · cited 1×
“…evade detection as ‘adversarial techniques’ in reference to the combination of methods that have been referred to as adversarial attacks in the extant literature related to attacks on machine learning based tools (Alsmadi et al., 2021; Qiu et al., 2019; Sadasivan et al., 2023; Wang et al., 2023).”
BackgroundPromptChainer: Chaining Large Language Model Prompts through Visual Programming
Wu, T., Jiang, E., Donsbach, A., Gray, J., Molina, A., Terry, M., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519729 · Cited by 198 · cited 1×
“Examples include the use of delimiters (Sweenor & Ramanathan, 2023) and prompt chaining (T. Wu et al., 2022).”
AI-generated research paper fabrication and plagiarism in the scientific community
Elali, F. R., & Rachid, L. N. (2023) · Patterns · doi:10.1016/j.patter.2023.100706 · Cited by 197 · cited 1×
“…to a lack of holistic understanding of the interplay between AI text detectors, GenAI models, and adversarial techniques (Anderson et al., 2023; Chaka, 2023b; Elali & Rachid, 2023; Elkhatat et al., 2023; Liang et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Weber-Wulff et al., 2023).”
ENAI Recommendations on the ethical use of Artificial Intelligence in Education
Foltynek, T., Bjelobaba, S., Glendinning, I., Khan, Z. R., Santos, R., Pavletic, P., & Kravjar, J. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00133-4 · Cited by 180 · cited 1×
“Simultaneously, a growing number of organisational bodies are now producing guidelines for the ethical use of GenAI in education (Foltynek et al., 2023; Miao & Holmes, 2023).”
Using Internet based paraphrasing tools: Original work, patchwriting or facilitated plagiarism?
Rogerson, A. M., & McCarthy, G. (2017) · International Journal for Educational Integrity · doi:10.1007/s40979-016-0013-y · Cited by 179 · cited 2×
“…in suspicion as to the author-ship of the work, similar to the ‘word salad’ that frequently appears following the use of an APT (Roe & Perkins, 2022; Rogerson & McCarthy, 2017) Decrease complexity (DC) This technique requested a simplification of a sample’s vocabulary and sentence structures,…”
A review of AWE feedback: types, learning outcomes, and implications
Fu, Q.-K., Zou, D., Xie, H., & Cheng, G. (2024) · Computer Assisted Language Learning · doi:10.1080/09588221.2022.2033787 · Cited by 170 · cited 2×
“For tasks involving multistep reasoning, Fu et al. (2022) concluded that Claude 2’s performance is comparable to that of GPT-4, with Lin and Chen (2023), claiming that Claude 2 slightly outperforms GPT-4.”
Anderson, N., Belavy, D. L., Perle, S. M., Hendricks, S., Hespanhol, L., Verhagen, E., & Memon, A. R. (2023) · BMJ Open Sport & Exercise Medicine · doi:10.1136/bmjsem-2023-001568 · Cited by 168 · cited 1×
“Existing research points to a lack of holistic understanding of the interplay between AI text detectors, GenAI models, and adversarial techniques (Anderson et al., 2023; Chaka, 2023b; Elali & Rachid, 2023; Elkhatat et al., 2023; Liang et al., 2023; Orenstrakh et al., 2023; Perkins, Roe, et al.,…”
BackgroundDetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
Mitchell, E., Lee, Y., Khazatsky, A., Manning, C. D., & Finn, C. (2023) · arXiv · doi:10.48550/arxiv.2301.11305 · Cited by 151
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Krishna, K., Song, Y., Karpinska, M., Wieting, J., & Iyyer, M. (2023) · arXiv · doi:10.48550/arxiv.2303.13408 · Cited by 150 · cited 3×
“All samples created were tested against seven AI text detectors which had been previously identified in literature (Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins, Roe, et al., 2023; Weber-Wulff et al., 2023)as being somewhat effective at successfully…”
MethodParaphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Krishna, K., Song, Y., Karpinska, M., Wieting, J., & Iyyer, M. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1195 · Cited by 150
Lozić, E., & Štular, B. (2023) · Future Internet · doi:10.3390/fi15100336 · Cited by 135 · cited 1×
“Despite these achievements, Claude 2 lags in scientific writing and quantitative accuracy compared to other models (Chang et al., 2023; Lozić & Štular, 2023; Z. Wu et al., 2023), primarily because of the ability of GPT-4 and Bard to access the internet for information gathering.”
(2023) · Journal of Applied Learning & Teaching · doi:10.37074/jalt.2023.6.2.12 · Cited by 132 · cited 4×
“(Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Walters, 2023; Weber-Wulff et al., 2023).”
InfluentialDo teachers spot AI? Evaluating the detectability of AI-generated texts among student essays
Fleckenstein, J., Meyer, J., Jansen, T., Keller, S. D., Köller, O., & Möller, J. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100209 · Cited by 126 · cited 1×
“This model represented a step-change in the abilities of GenAI to create text that was significantly more difficult to detect by educators (Fleckenstein et al., 2024; Perkins et al., 2023), and thus the technology began to draw greater attention in the public sphere, as well as in educational…”
Academic publisher guidelines on AI usage: A ChatGPT supported thematic analysis
Perkins, M., & Roe, J. (2024) · F1000Research · doi:10.12688/f1000research.142411.2 · Cited by 123 · cited 3×
“…in enhancing academic practices for both students and teachers alike, and most publishing houses now permit the transparent use of such tools (Perkins & Roe, 2024a), there are circumstances in which the detection of GenAI texts remains necessary, such as in assessment practices which do not…”
BackgroundSelf-citationWalters, W. H. (2023) · Open Information Science · doi:10.1515/opis-2022-0158 · Cited by 109 · cited 3×
“While some of these tools are free and others require either registration or payment, research by Walters (2023) has identified that the accuracy of paid-for tools is only slightly higher than that of free versions.”
Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover
Fröhling, L., & Zubiaga, A. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.443 · Cited by 106
Lancaster, T. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00131-6 · Cited by 103 · cited 1×
“Lancaster (2023) proposed that watermarking AI-generated text may be a potential solution; however, the attacks discussed above demonstrate that even LLMs protected by watermarking schemes are vulnerable to manipulation of this type.”
Time well spent: Creating a community of inquiry in blended first-year writing courses
Hilliard, L., & Stewart, M. K. (2018) · The Internet and Higher Education · doi:10.1016/j.iheduc.2018.11.002 · Cited by 102 · cited 1×
“Similar to blended learning and communities of enquiry that contribute to the reori-entation of the traditional classroom structure (Hilliard & Stewart, 2019), the presence of multiple forms of media on the Internet prompts us to reconsider the reliability and usefulness of source materials in the…”
The AI Assessment Scale (AIAS) in action: A pilot implementation of GenAI supported assessment
Furze, L., Perkins, M., Roe, J., & MacVaugh, J. (2024) · Australasian Journal of Educational Technology · doi:10.14742/ajet.9434 · Cited by 92 · cited 1×
“…Scale (Perkins, Furze, et al., 2023), where the expected use of AI in any given assessment is clearly stated, could help guide educators in adapting assessment practices to align with the AI era, potentially leading to increased student outcomes and pedagogical redesign (Furze et al., 2024).”
BackgroundSelf-citationBedington, A., Halcomb, E. F., McKee, H. A., Sargent, T., & Smith, A. (2024) · Computers & composition/Computers and composition · doi:10.1016/j.compcom.2024.102833 · Cited by 89 · cited 1×
“…which accepts the use of GenAI in crafting manuscripts, albeit with certain restrictions (Per-kins & Roe, 2024a), and studies have shown the rising popularity of using GenAI tools to support academic writing and research (Bedington et al., 2024; Chan, 2023; Perkins & Roe, 2024b; Sobaih, 2024).”
Roe, J., & Perkins, M. (2022) · International Journal for Educational Integrity · doi:10.1007/s40979-022-00109-w · Cited by 83 · cited 6×
“…which may result in suspicion as to the author-ship of the work, similar to the ‘word salad’ that frequently appears following the use of an APT (Roe & Perkins, 2022; Rogerson & McCarthy, 2017) Decrease complexity (DC) This technique requested a simplification of a sample’s vocabulary and…”
InfluentialSelf-citationDetecting LLM-Generated Text in Computing Education: Comparative Study for ChatGPT Cases
Orenstrakh, M. S., Karnalim, O., Suárez, C. A., & Liut, M. (2024) · 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00027 · Cited by 79
Case study: suggesting choice: inclusive assessment processes
Morris, C., Milton, E., & Goldstone, R. (2019) · Higher Education Pedagogies · doi:10.1080/23752696.2019.1669479 · Cited by 76 · cited 2×
“Research has shown that the assuredness of fairness and equity is vital for inclusive assessment practices (Morris et al., 2019), and notions of fairness and security suggest that students will not be able to misrepresent authorship and thus gain educational outcomes that they have not earned.”
Battle of the Wordsmiths: Comparing ChatGPT, GPT-4, Claude, and BardPreprint
Borji, A., & Mohammadian, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4476855 · Cited by 75 · cited 1×
“By manipulating FM text output, and evaluating the performance of AI text detection technology, we address an educational problem.”
The use of Generative AI in qualitative analysis: Inductive thematic analysis with ChatGPT
(2024) · Journal of Applied Learning & Teaching · doi:10.37074/jalt.2024.7.1.22 · Cited by 70 · cited 1×
“…which accepts the use of GenAI in crafting manuscripts, albeit with certain restrictions (Per-kins & Roe, 2024a), and studies have shown the rising popularity of using GenAI tools to support academic writing and research (Bedington et al., 2024; Chan, 2023; Perkins & Roe, 2024b; Sobaih, 2024).”
Self-citationAssisting academics to identify computer generated writing
Abd-Elaal, E.-S., Gamage, S. H. P. W., & Mills, J. E. (2022) · European Journal of Engineering Education · doi:10.1080/03043797.2022.2046709 · Cited by 62 · cited 1×
“In doing so, we address the need for a standardised framework and taxonomy to compare and evaluate the performance of AI text detectors against GenAI tools and adversarial techniques (Abd-Elaal et al., 2022).”
Wu, Z., Qiu, L., Ross, A., Akyürek, E., Chen, B., Wang, B., Kim, N., Andreas, J., & Kim, Y. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.102 · Cited by 58
Chaka, C. (2023) · International Journal of Learning Teaching and Educational Research · doi:10.26803/ijlter.22.6.1 · Cited by 50 · cited 4×
“(Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Walters, 2023; Weber-Wulff et al., 2023).”
InfluentialGuidance for generative AI in education and research
Miao, F., & Holmes, W. (2023) · UCL Discovery (University College London) · Cited by 46
The EAP‐AIAS: Adapting the AI Assessment Scale for English for Academic Purposes
Roe, J., Perkins, M., & Tregubova, Y. (2026) · TESOL Journal · doi:10.1002/tesj.70122 · Cited by 39 · cited 1×
“Strategies such as the AI Assessment Scale (Furze et al., 2024; Per-kins et al., 2024a; Roe et al., 2024), where the expected use of AI in any given assessment is clearly stated, could help guide educators in adapting assessment practices to align with the AI era, potentially leading to increased…”
Self-citationBissessar, C. (2026) · Equity in Education & Society · doi:10.1177/27526461231215083 · Cited by 34 · cited 1×
“Further, Bissessar (2023) also identifies the digital divide as an important consideration in the use of GenAI tools in classroom settings and Liang (2023) recognises that GenAI tools are known for producing structurally biased and ethnocentric worldviews.”
Testing of Detection Tools for AI-Generated Text
Weber-Wulff, D., Anohina-Naumeca, A., Bjelobaba, S., Foltýnek, T., Guerrero-Dib, J., Popoola, O., Šigut, P., & Waddington, L. (2023) · arXiv · doi:10.48550/arxiv.2306.15666 · Cited by 32 · cited 8×
“…were tested against seven AI text detectors which had been previously identified in literature (Chaka, 2023a; Gao et al., 2022; Krishna et al., 2023; Orenstrakh et al., 2023; Perkins et al., 2023; Weber-Wulff et al., 2023) as being somewhat effective at successfully identifying GenAI content.”
InfluentialSobaih, A. E. (2024) · Journal of Applied Learning & Teaching · doi:10.37074/jalt.2024.7.1.21 · Cited by 31 · cited 1×
“…which accepts the use of GenAI in crafting manuscripts, albeit with certain restrictions (Per-kins & Roe, 2024a), and studies have shown the rising popularity of using GenAI tools to support academic writing and research (Bedington et al., 2024; Chan, 2023; Perkins & Roe, 2024b; Sobaih, 2024).”
Wu, Z., Qiu, L., Ross, A., Akyürek, E., Chen, B., Wang, B., Kim, N., Andreas, J., & Kim, Y. (2023) · arXiv · doi:10.48550/arxiv.2307.02477 · Cited by 19 · cited 1×
“Despite these achievements, Claude 2 lags in scientific writing and quantitative accuracy compared to other models (Chang et al., 2023; Lozić & Štular, 2023; Z. Wu et al., 2023), primarily because of the ability of GPT-4 and Bard to access the internet for information gathering.”
MethodAlsmadi, I. M., Ahmad, K., Nazzal, M., Alam, F., Al‐Fuqaha, A., Khreishah, A. A., & Algosaibi, A. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13980 · Cited by 13 · cited 1×
“…evade detection as ‘adversarial techniques’ in reference to the combination of methods that have been referred to as adversarial attacks in the extant literature related to attacks on machine learning based tools (Alsmadi et al., 2021; Qiu et al., 2019; Sadasivan et al., 2023; Wang et al., 2023).”
BackgroundDetecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT CasesPreprint
Orenstrakh, M. S., Karnalim, O., Suárez, C. A., & Liut, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.07411 · Cited by 13
Unconventional sources as a new convention: The shifting paradigm of undergraduate writing
Radia, P., & Stapleton, P. (2009) · The Internet and Higher Education · doi:10.1016/j.iheduc.2009.05.002 · Cited by 8
Prevalence, Incidence, and Rates of Contract Cheating
Curtis, G. J., & Clare, J. (2024) · Springer International Handbooks of Education · doi:10.1007/978-3-031-54144-5_110 · Cited by 6
Roe, J., & Perkins, M. (2023) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00138-z · Cited by 5
Self-citationDaly, T. M., & Ryan, J. C. (2024) · International Journal for Educational Integrity · doi:10.1007/s40979-023-00148-x · Cited by 4 · cited 1×
“…Perkins, 2023), and complex cases of fraud, such as contract cheating, continue to create unequal opportunities and outcomes (Curtis & Clare, 2024; Daly & Ryan, 2024); thus, efforts to promote inclusive forms of participation in higher education cannot solely focus on GenAI, as traditional,…”
BackgroundPerkins, M., Roe, J., Vu, H. B., Postma, D., Hickerson, D., McGaughran, J., & Khuat, Q. H. (2024) · Data Archiving and Networked Services (DANS) · doi:10.17632/xv6fk2mmh9 · Cited by 1
Self-citationPerkins, M., & Roe, J. (2024) · doi:10.5256/f1000research.160745.r238284
Self-citationLin, Y.-T., & Chen, Y.-N. (2023) · arXiv · doi:10.48550/arxiv.2305.13711 · cited 2×
“For tasks involving multistep reasoning, Fu et al. (2022) concluded that Claude 2's performance is comparable to that of GPT-4, with Lin and Chen (2023), claiming that Claude 2 slightly outperforms GPT-4.”
BackgroundFurze, L., Perkins, M., Roe, J., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.14692
Self-citationData files: Simple Techniques to Bypass GenAI Text Detectors: Implications for Inclusive Education
Perkins, M., Roe, J., Vu, H. B., et al. (2024) · Mendeley Data · doi:10.17632/xv6fk2mmh9.3
Self-citationThe EAP-AIAS: Adapting the AI Assessment Scale for English for Academic Purposes
Roe, J., Perkins, M., & Tregubova, Y. (2024) · arXiv · doi:10.48550/arxiv.2408.01075
Self-citation
Research works printed but not linked: 3
- Originality.AI. (2023). AI Content Detector Accuracy Review + Open Source Dataset and Research Tool – Originality.AI. https://originality.ai
- Roe, J. (2024). AI and the Anthropological Imagination: Rethinking Education in the Digital Age. Open Anthropology Research Repository. https://openanthroresearch.org/index.php/oarr/preprint/view/399
- Sweenor, D., & Ramanathan, K. (2023). The CIO’s Guide to Adopting Generative AI: Five Keys to Success. TinyTechMedia LLC.
Cited by
Talk is cheap: why structural assessment changes are needed for a time of GenAI
Corbin, T., Dawson, P., & Liu, D. (2025) · Assessment & Evaluation in Higher Education · doi:10.1080/02602938.2025.2503964 · Cited by 107
The AI Assessment Scale (AIAS) in action: A pilot implementation of GenAI supported assessment
Furze, L., Perkins, M., Roe, J., & MacVaugh, J. (2024) · Australasian Journal of Educational Technology · doi:10.14742/ajet.9434 · Cited by 92
Self-citationGenerative AI tools and empowerment in L2 academic writing
Moorhouse, B. L., Wan, Y., Wu, C., Wu, M., & Ho, T. Y. (2025) · System · doi:10.1016/j.system.2025.103779 · Cited by 63
Bjelobaba, S., Waddington, L., Perkins, M., Foltýnek, T., Bhattacharyya, S., & Weber-Wulff, D. (2025) · International Journal for Educational Integrity · doi:10.1007/s40979-025-00191-w · Cited by 118
“…is not recommended owing to inherent problems with interpretation of the results, accuracy, and bias (Liang, 2023, Weber-Wulff et al. 2023; Perkins et al. 2024a, b), it is worth noting that the reliability of the detectors significantly drops if machine translation is used on human…”
Self-citationGenerative artificial intelligence: implications for biomedical and health professions education
Hersh, W. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-094756 · Cited by 28
Metadata
- Authors
- Perkins, M., Roe, J., Vu, B. H., Postma, D., Hickerson, D., McGaughran, J., & Khuat, H. Q.
- Affiliations
- British University Vietnam (VN)
- James Cook University Singapore (SG)
- Corresponding author
- Perkins, Mike
- Venue
- International Journal of Educational Technology in Higher Education
- Published
- 2024-09-09
- Volume
- 21
- Issue
- 1
- ISSN
- 2365-9440 (ISSN-L)
- OpenAlex
- W4402340204
- Cited by
- 117
- References
- 53
- Citations by year
- 2026: 64 · 2025: 47 · 2024: 6
- FWCI
- 48.31
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- International Journal of Educational Technology in Higher Education (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- ResearchOnline - JCU (James Cook University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Durham Research Online (Durham University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Education › Academic integrity and plagiarism
- Social Sciences › Education › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Keywords
- academic integrity, false accusation, inclusive assessment, higher education, assessment fairness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.