Adversarial Attacks Against Deep Learning-Based Network Intrusion Detection Systems and Defense Mechanisms
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Neural networks (NNs) are increasingly popular in developing NIDS, yet can prove vulnerable to adversarial examples. Through these, attackers that may be oblivious to the precise mechanics of the targeted NIDS add subtle perturbations to malicious traffic features, with the aim of evading detection and disrupting critical systems. Defending against such adversarial attacks is of high importance, but requires to address daunting challenges. Here, we introduce TIKI- TAKA, a general framework for(i)assessing the robustness of state-of-the-art deep learning-based NIDS against adversarial manipulations, and which(ii)incorporates defense mechanisms that we propose to increase resistance to attacks employing such evasion techniques. Specifically, we select five cutting-edge adversarial attack types to subvert three popular malicious traffic detectors that employ NNs. We experiment with publicly available datasets and consider both one-to-all and one-to-one classification scenarios, i.e., discriminating illicit vs benign traffic and respectively identifying specific types of anomalous traffic among many observed. The results obtained reveal that attackers can evade NIDS with up to 35.7% success rates, by only altering time-based features of the traffic generated. To counteract these weaknesses, we propose three defense mechanisms: model voting ensembling, ensembling adversarial training, and query detection. We demonstrate that these methods can restore intrusion detection rates to nearly 100% against most types of malicious traffic, and attacks with potentially catastrophic consequences (e.g., botnet) can be thwarted. This confirms the effectiveness of our solutions and makes the case for their adoption when designing robust and reliable deep anomaly detectors.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · cited 1×
“generate adversarial samples in black-box settings [28] using three types of approaches, namely surrogate models [29], Zeroth Order Optimization (ZOO) [30], and Generative Adversarial Networks (GANs) [31].”
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 · cited 1×
“This has been also confirmed with adversarial attacks against image classifiers [60], and implies that, even with completely different structures, NID models suffer from similar weaknesses, which attackers can exploit.”
A detailed analysis of the KDD CUP 99 data set
Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A. A. (2009) · 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications · doi:10.1109/cisda.2009.5356528 · Cited by 5,396
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization
Sharafaldin, I., Habibi Lashkari, A., & Ghorbani, A. A. (2018) · Proceedings of the 4th International Conference on Information Systems Security and Privacy · doi:10.5220/0006639801080116 · Cited by 5,318
A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection
Buczak, A. L., & Guven, E. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2015.2494502 · Cited by 3,332
One Pixel Attack for Fooling Deep Neural Networks
Su, J., Vargas, D. V., & Sakurai, K. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2890858 · Cited by 2,406 · cited 1×
“3139% Total 16,846,014 100% subset that may change flow semantics remain unchanged during the attack, which is inline with recent research confirming that adversarial samples can be constructed effectively by perturbing only a small subset of the input features [46].”
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176 · cited 4×
“Commonly used meth-ods include Network Distillation [36], Adversarial Training [37], Adversarial Detecting [38], Input Reconstruction [39], Classifier Robustifying [40], Network Verification [41], and an ensemble of them [11], [42], which work either reactively or proactively.”
InfluentialA Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks
Yin, C., Zhu, Y., Fei, J., & He, X. (2017) · IEEE Access · doi:10.1109/access.2017.2762418 · Cited by 2,100 · cited 1×
“Recurrent Neural Networks (RNNs) are popular candidates for extracting temporal features of traffic flows [22].”
Cited by
Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey
He, K., Kim, D. D., & Asghar, M. R. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3233793 · Cited by 450
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
Nageshwaran, V., & Ezekiel, S. (2026) · doi:10.20944/preprints202606.0142.v1 · Cited by 4
Metadata
- Authors
- Zhang, C., Costa-Perez, X., & Patras, P.
- Venue
- IEEE/ACM Transactions on Networking
- Published
- 2022-06
- Volume
- 30
- Issue
- 3
- Pages
- 1294-1311
- ISSN
- 1063-6692 (ISSN-L)
- 1558-2566
- OpenAlex
- W4206331418
- Cited by
- 195
- References
- 19
- FWCI
- 12.04
- Type
- journal article
- Language
- en
- Open access
- green
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.