Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Open accessThe DOI matches its Crossref record; 33 of the 35 references it cites were found in a registry or an index.
Abstract
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems. Given that DNNs are now able to classify objects in images with near-human-level performance, questions naturally arise as to what differences remain between computer and human vision. A recent study [30] revealed that changing an image (e.g. of a lion) in a way imperceptible to humans can cause a DNN to label the image as something else entirely (e.g. mislabeling a lion a library). Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion). Specifically, we take convolutional neural networks trained to perform well on either the ImageNet or MNIST datasets and then find images with evolutionary algorithms or gradient ascent that DNNs label with high confidence as belonging to each dataset class. It is possible to produce images totally unrecognizable to human eyes that DNNs believe with near certainty are familiar objects, which we call “fooling images” (more generally, fooling examples). Our results shed light on interesting differences between human vision and current DNNs, and raise questions about the generality of DNN computer vision.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“However, some AI weaknesses have proved surprisingly difficult to solve, such as AI being easily fooled41,42 and overconfidently wrong (hallucinations)43, although progress has been made44,45.”
From Towards end-to-end automation of AI research (2026) · cites this paper as [41]
In the citing paper
“Divergence between epistemic standards seems entirely legitimate, for instance, given widespread debates about the soundness and robustness of machine learning models”
From Algorithmic Accountability and Public Reason (2018) · cites this paper as Nguyen, Yosinski, & Clune, 2015
In the citing paper
“This simply implies that domestic legislation must serve as the principal source for the substantive law relating to the use of AI in space [245].”
From Applications and Challenges of Artificial Intelligence in Space Missions (2024) · cites this paper as [245]
In the citing paper
“Liability under the space law treaty regime is grounded in Outer Space Treaty (OST) Article VIII, which is the genesis of the Liability Convention [245].”
From Applications and Challenges of Artificial Intelligence in Space Missions (2024) · cites this paper as [245]
In the citing paper
“There are no international or space treaties that address or regulate the use of AI in space.”
From Applications and Challenges of Artificial Intelligence in Space Missions (2024) · cites this paper as [245]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Multi-Objective Optimization Using Evolutionary Algorithms
Deb, K., & Kalyanmoy, D. (2001) · Andalas University Repository (Andalas University) · Cited by 17,323
(2010) · International Conference on Machine Learning · Cited by 13,995
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Research works printed but not linked: 2
- erhan, 2009, Visualizing higher-layer features of a deep network, Dept IRO Universite de Montreal Tech Rep
- mouret, 2010, Sferes v2: Evolvin'in the multi-core world, Evolutionary Computation (CEC) 2010 IEEE Congress on, 4079
Cited by
Items 901–1,000 of 1,015
Attack as defense: characterizing adversarial examples using robustness
Zhao, Z., Chen, G., Wang, J., Yang, Y., Song, F., & Sun, J. (2021) · ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) · doi:10.1145/3460319.3464822 · Cited by 43
Socially intelligent machines that learn from humans and help humans learn
Gweon, H., Fan, J. E., & Kim, B. (2023) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2022.0048 · Cited by 43
Solving Bongard Problems With a Visual Language and Pragmatic Constraints
Depeweg, S., Rothkopf, C. A., & Jäkel, F. (2024) · Cognitive Science · doi:10.1111/cogs.13432 · Cited by 43
Visualization Methods for Image Transformation Convolutional Neural Networks
Protas, É., Bratti, J., Gaya, J. F. D. O., Drews, P., & Botelho, S. S. D. C. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2881194 · Cited by 43
How hard is it to cross the room? -- Training (Recurrent) Neural Networks to steer a UAVPreprint
Kelchtermans, K., & Tuytelaars, T. (2017) · Lirias · doi:10.48550/arxiv.1702.07600 · Cited by 43
Understanding the One-Pixel Attack: Propagation Maps and Locality AnalysisPreprint
Vargas, D. V., & Su, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02947 · Cited by 43
No True State-of-the-Art? OOD Detection Methods are Inconsistent across DatasetsPreprint
Tajwar, F., Kumar, A., Xie, S. M., & Liang, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05554 · Cited by 43
Random Weight Factorization Improves the Training of Continuous Neural RepresentationsPreprint
Wang, S., Wang, H., Seidman, J. H., & Perdikaris, P. G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.01274 · Cited by 43
Butz, M. V. (2021) · KI - Künstliche Intelligenz · doi:10.1007/s13218-021-00705-x · Cited by 42
“Furthermore, despite the best efforts over the last years, deep learning is still easily fooled [74], that is, it remains very hard to make any guarantees about how the system will behave given data that departs from the training set statistics.”
BackgroundResisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders
Ghosh, P. S., Losalka, A., & Black, M. J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301541 · Cited by 42
Reliable detection of compressed and encrypted data
Gaspari, F. D., Hitaj, D., Pagnotta, G., Carli, L. D., & Mancini, L. V. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07586-7 · Cited by 42
Music Mood Dataset Creation Based on Last FM Tags
Çano, E., & Morisio, M. (2017) · doi:10.5121/csit.2017.70603 · Cited by 42
Floating-Point Multiplication Timing Attack on Deep Neural Network
Dong, G., Wang, P., Chen, P., Gu, R., & Hu, H. (2019) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot.2019.00032 · Cited by 42
Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
Han, J., Dong, X., Zhang, R., Chen, D., Zhang, W., Yu, N., Luo, P., & Wang, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00526 · Cited by 42
CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issue
Tang, K., Miao, D., Peng, W., Wu, J., Shi, Y., Gu, Z., Tian, Z., & Wang, W. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00119 · Cited by 42
PremiUm-CNN: Propagating Uncertainty Towards Robust Convolutional Neural Networks
Dera, D., Bouaynaya, N. C., Rasool, G., Shterenberg, R., & Fathallah‐Shaykh, H. M. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3096804 · Cited by 42
Phan, H., & Nguyen, A. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01962 · Cited by 42
Self-citationRahman, M. A., & Haque, B. M. T. (2022) · doi:10.63125/9hd4e011 · Cited by 42
Blackwell, A. F. (2015) · Aarhus Series on Human Centered Computing · doi:10.7146/aahcc.v1i1.21197 · Cited by 42
A novel biomedical image indexing and retrieval system via deep preference learning
Pang, S., Orgun, M. A., & Yu, Z. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.02.003 · Cited by 42
Cammarata, N., Goh, G., Carter, S., Schubert, L., Petrov, M., & Olah, C. (2020) · Distill · doi:10.23915/distill.00024.003 · Cited by 41
Conditioning by adaptive sampling for robust design
Brookes, D. H., Park, H., & Listgarten, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10060 · Cited by 41
Denoising Autoencoders for Overgeneralization in Neural Networks
Spigler, G. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2909876 · Cited by 41
Towards Representative Web Performance Measurements with Google Lighthouse
Heričko, T., Šumak, B., & Brdnik, S. (2021) · doi:10.18690/978-961-286-516-0.9 · Cited by 41
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart
Pang, T., Zhang, H., He, D., Dong, Y., Su, H., Chen, W., Zhu, J., & Liu, T. Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01479 · Cited by 41
Cao, L. (2023) · International Journal of Data Science and Analytics · doi:10.1007/s41060-023-00383-y · Cited by 41
Learning Discriminative Representations and Decision Boundaries for Open Intent Detection
Zhang, H., Xu, H., Zhao, S., & Zhou, Q. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3265203 · Cited by 41
Deep integrative models for large-scale human genomics
Sigurdsson, A. I., Louloudis, I. E., Banasik, K., Westergaard, D., Winther, O., Lund, O., Ostrowski, S. R., Erikstrup, C., Pedersen, O. B., Nyegaard, M., et al. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad373 · Cited by 41
DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models
Gao, R., Zhao, C., Hong, L., & Xu, Q. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00152 · Cited by 41
Evolution of artistic image variants through feature based diversity optimisation
Alexander, B., Kortman, J., & Neumann, A. (2017) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3071178.3071342 · Cited by 41
Mitigating fooling with competitive overcomplete output layer neural networks
Kardan, N., & Stanley, K. O. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7965897 · Cited by 41
FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning
Khalid, F., Hanif, M. A., Rehman, S., Qadir, J., & Shafique, M. (2019) · Design, Automation, and Test in Europe · doi:10.23919/date.2019.8715141 · Cited by 41
Anatomical context protects deep learning from adversarial perturbations in medical imaging
Li, Y., Zhang, H., Bermudez, C. L., Chen, Y., Landman, B. A., & Vorobeychik, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.085 · Cited by 41
Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone MappingPreprint
Hou, X., Duan, J., & Qiu, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.09482 · Cited by 41
A Critical Investigation of Deep Reinforcement Learning for NavigationPreprint
Dhiman, V., Banerjee, S., Griffin, B., Siskind, J. M., & Corso, J. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.02274 · Cited by 41
Safeguarding Vision-Language Models Against Patched Visual Prompt InjectorsPreprint
Sun, J., Wang, C., Wang, J., Zhang, Y., & Xiao, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.10529 · Cited by 41
Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
Minervini, P., & Riedel, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08609 · Cited by 40
Improving the interpretability of deep neural networks with stimulated learning
Tan, S., Sim, K. C., & Gales, M. (2015) · 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404853 · Cited by 40
Fréchet AutoEncoder Distance: A new approach for evaluation of Generative Adversarial Networks
Buzuti, L. F., & Thomaz, C. E. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103768 · Cited by 40
Open-World Semantic Segmentation Including Class Similarity
Sodano, M., Magistri, F., Nunes, L., Behley, J., & Stachniss, C. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00307 · Cited by 40
Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Heng, A. J. R., Thiéry, A. H., & Soh, H. (2024) · neural information processing systems · doi:10.52202/079017-1395 · Cited by 40
Behpour, S., Doan, T. L., Li, X., He, W., Gou, L., & Ren, L. (2023) · neural information processing systems · doi:10.52202/075280-1659 · Cited by 40
Lokhande, V. S., Tasneeyapant, S., Venkatesh, A., Ravi, S. N., & Singh, V. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01145 · Cited by 40
Out-of-Distribution Detection of Human Activity Recognition with Smartwatch Inertial Sensors
Boyer, P., Burns, D., & Whyne, C. M. (2021) · Sensors · doi:10.3390/s21051669 · Cited by 40
Semantic Perceptual Image Compression With a Laplacian Pyramid of Convolutional Networks
Wang, J., Duan, Y., Tao, X., Xu, M., & Lü, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3065244 · Cited by 40
Automated data validation in machine learning systems
Bießmann, F., Gołębiowski, J., Rukat, T., Lange, D., & Schmidt, P. S. (2021) · Cited by 40
Li, Y., Zhao, D., & Zeng, Y. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.991851 · Cited by 40
Aerodynamic Design Exploration through Surrogate-Assisted Illumination
Gaier, A., Asteroth, A., & Mouret, J.-B. (2017) · AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference (MAO) · doi:10.2514/6.2017-3330 · Cited by 40
Confident Multiple Choice LearningPreprint
Lee, K., Hwang, C., Park, K., & Shin, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.03475 · Cited by 40
Browne, K., & Swift, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10076 · Cited by 40
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature VisualizationPreprint
Borowski, J., Zimmermann, R. S., Schepers, J., Geirhos, R., Wallis, T. S. A., Bethge, M., & Brendel, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12606 · Cited by 40
Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
Dong, Y., Su, H., Zhu, J. J., & Bao, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.05493 · Cited by 39
Continual Evidential Deep Learning for Out-of-Distribution Detection
Aguilar, E., Raducanu, B., Radeva, P. I., & van de Weijer, J. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00369 · Cited by 39
LAPT: Label-Driven Automated Prompt Tuning for OOD Detection with Vision-Language Models
Zhang, Y., Zhu, W., He, C., & Zhang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73220-1_16 · Cited by 39
Defending DNN Adversarial Attacks with Pruning and Logits Augmentation
Wang, S., Wang, X., Ye, S., Zhao, P., & Lin, X. (2018) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2018.8646578 · Cited by 39
Chessel, A., & Salas, R. E. C. (2019) · Essays in Biochemistry · doi:10.1042/ebc20180044 · Cited by 39
Deep learning for 3D imaging and image analysis in biomineralization research
Reznikov, N., Buss, D. J., Provencher, B., McKee, M. D., & Piché, N. (2020) · Journal of Structural Biology · doi:10.1016/j.jsb.2020.107598 · Cited by 39
Robust Deep Learning Ensemble against Deception
Wei, W., & Liu, L. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3024660 · Cited by 39
Interpreting Image Classifiers by Generating Discrete Masks
Yuan, H., Cai, L., Hu, X., Wang, J., & Ji, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3028783 · Cited by 39
Explainable AI for medical imaging: explaining pneumothorax diagnoses with Bayesian teaching
Folke, T., Yang, S. C., Anderson, S. P., & Shafto, P. (2021) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2585967 · Cited by 39
Degradation stage classification via interpretable feature learning
Alfeo, A. L., Cimino, M. G. C. A., & Vaglini, G. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.05.003 · Cited by 39
Uncertainty quantification for deep learning in particle accelerator applications
Mishra, A., Edelen, A. L., Hanuka, A., & Mayes, C. (2021) · Physical Review Accelerators and Beams · doi:10.1103/physrevaccelbeams.24.114601 · Cited by 39
Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness
Coletta, A., Jerome, J., Savani, R., & Vyetrenko, S. (2023) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3604237.3626854 · Cited by 39
Understanding natural scenes: Contributions of image statistics
Cesarei, A. D., Loftus, G. R., Mastria, S., & Codispoti, M. (2017) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2017.01.012 · Cited by 39
On the development of intelligent optical inspections
Richter, J., Streitferdt, D., & Rozova, E. (2017) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc.2017.7868455 · Cited by 39
Detecting Adversarial Examples and Other Misclassifications in Neural Networks by IntrospectionPreprint
Aigrain, J., & Detyniecki, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.09186 · Cited by 39
Overinterpretation reveals image classification model pathologiesPreprint
Carter, B., Jain, S., Mueller, J. W., & Gifford, D. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08907 · Cited by 39
The limits and potentials of deep learning for robotics
Sünderhauf, N., Brock, O., Scheirer, W., Hadsell, R., Fox, D., Leitner, J., Upcroft, B., Abbeel, P., Burgard, W., Milford, M., et al. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918770733 · Cited by 38
“If for example an object detection system is fooled by data outside of its training data distribution [35], [79], the consequences for a robot acting on false, but high-confidence detections can be catastrophic.”
BackgroundChittajallu, D. R., Dong, B., Tunison, P., Collins, R., Wells, K., Fleshman, J., Sankaranarayanan, G., Schwaitzberg, S., Cavuoto, L., & Enquobahrie, A. (2019) · 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) · doi:10.1109/isbi.2019.8759428 · Cited by 38
Mind control attack: Undermining deep learning with GPU memory exploitation
Park, S.-O., Kwon, O., Kim, Y., Kil, S., & Yoon, H. (2020) · Computers & Security · doi:10.1016/j.cose.2020.102115 · Cited by 38
Neuromorphic visual scene understanding with resonator networks
Renner, A., Supic, L., Danielescu, A., Indiveri, G., Olshausen, B. A., Sandamirskaya, Y., Sommer, F. T., & Frady, E. P. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00848-0 · Cited by 38
Bonato, J., Cotogni, M., & Sabetta, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73232-4_1 · Cited by 38
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
Zhang, Y., & Zhang, L. (2024) · neural information processing systems · doi:10.52202/079017-1224 · Cited by 38
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Bibi, A., Alfadly, M., & Ghanem, B. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00948 · Cited by 38
Towards Interpretable Object Detection by Unfolding Latent Structures
Wu, T., & Song, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00613 · Cited by 38
binary junipr: An Interpretable Probabilistic Model for Discrimination
Andreassen, A., Feige, I., Frye, C., & Schwartz, M. D. (2019) · Physical Review Letters · doi:10.1103/physrevlett.123.182001 · Cited by 38
Polishing Decision-Based Adversarial Noise With a Customized Sampling
Shi, Y., Han, Y., & Tian, Q. C. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00111 · Cited by 38
High Intrinsic Dimensionality Facilitates Adversarial Attack: Theoretical Evidence
Amsaleg, L., Bailey, J., Barbe, A., Erfani, S., Furon, T., Houle, M. E., Radovanović, M., & Nguyen, X. V. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3023274 · Cited by 38
Capture the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks
Hitaj, D., Hitaj, B., Jajodia, S., & Mancini, L. V. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.3036156 · Cited by 38
BET: black-box efficient testing for convolutional neural networks
Wang, J., Qiu, H., Rong, Y., Ye, H., Li, Q. L., Li, Z., & Zhang, C. (2022) · ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) · doi:10.1145/3533767.3534386 · Cited by 38
Kanwal, N., López-Pérez, M., Kiraz, U., Zuiverloon, T. C. M., Molina, R., & Engan, K. (2023) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2023.102321 · Cited by 38
Focusing on What is Relevant: Time-Series Learning and Understanding using Attention
Vinayavekhin, P., Chaudhury, S., Munawar, A., Agravante, D. J., Magistris, G. D., Kimura, D., & Tachibana, R. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545288 · Cited by 38
Toward Anthropomorphic Machine Learning
Angelov, P. P., & Gu, X. (2018) · Computer · doi:10.1109/mc.2018.3620973 · Cited by 38
Weakly supervised precise segmentation for historical document images
Xie, Z., Huang, Y., Jin, L., Liu, Y., Zhu, Y., Gao, L., & Zhang, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.001 · Cited by 38
Salience Models: A Computational Cognitive Neuroscience Review
Krasovskaya, S., & MacInnes, W. J. (2019) · Vision · doi:10.3390/vision3040056 · Cited by 38
Como funciona o Deep LearningPreprint
Ponti, M. A., & da Costa, G. B. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.07908 · Cited by 38
How to Not Measure DisentanglementPreprint
Sepliarskaia, A., Kiseleva, J., & de Rijke, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.05587 · Cited by 38
Rizvi, S. K. J., Azad, M. A., & Fraz, M. M. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09543-4 · Cited by 37
Maas, M. M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278766 · Cited by 37
Hilton, J., Cammarata, N., Carter, S., Goh, G., & Olah, C. (2020) · Distill · doi:10.23915/distill.00029 · Cited by 37
Deep Weighted Averaging Classifiers
Card, D., Zhang, M., & Smith, N. A. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287595 · Cited by 37
Deep learning in biomedical informatics
Hung, C. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-85796-3.00011-1 · Cited by 37
Generative Diffusion for Regional Surrogate Models From Sea‐Ice Simulations
Finn, T. S., Durand, C., Farchi, A., Bocquet, M., Rampal, P., & Carrassi, A. (2024) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004395 · Cited by 37
Dataset artefacts in anti-spoofing systems: A case study on the ASVspoof 2017 benchmark
Chettri, B., Benetos, E., & Sturm, B. L. T. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3036777 · Cited by 35
“models using adversarial machine learning is an active research topic [59]–[61].”
MethodAre Perceptually-Aligned Gradients a General Property of Robust Classifiers?
Kaur, S., Cohen, J., & Lipton, Z. C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08640 · Cited by 35
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
Cheney, N., Schrimpf, M., & Kreiman, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.08245 · Cited by 35
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
Yang, F., Du, M., & Hu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06831 · Cited by 34
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
Kristiadi, A., Hein, M., & Hennig, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10118 · Cited by 31
Extendable and explainable deep learning for pan-cancer radiogenomics research
Liu, Q., & Hu, P. (2022) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2021.102111 · Cited by 27
Aesthetics of Neural Network Art
Hertzmann, A. (2019) · arXiv · doi:10.48550/arxiv.1903.05696 · Cited by 21
Metadata
- Authors
- Nguyen, A., Yosinski, J., & Clune, J.
- Affiliations
- University of Wyoming (US)
- Cornell University (US)
- ORCID
- Clune, Jeff
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 427-436
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1932198206
- Cited by
- 3,258
- References
- 35
- Citations by year
- 2026: 73 · 2025: 210 · 2024: 313 · 2023: 323 · 2022: 318 · 2021: 460 · 2020: 401 · 2019: 407 · 2018: 348 · 2017: 211 · 2016: 124 · 2015: 60
- FWCI
- 139.54
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Aeronautics and Space Administration
- University of Wyoming
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- deep neural network robustness, adversarial examples, evolutionary algorithms, gradient ascent, ImageNet, MNIST, visual categorization
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.
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.