The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
NIC: Detecting Adversarial Samples with Neural Network Invariant Checking
Open accessAbstract
Deep Neural Networks (DNN) are vulnerable to adversarial samples that are generated by perturbing correctly classified inputs to cause DNN models to misbehave (e.g., misclassification).This can potentially lead to disastrous consequences especially in security-sensitive applications.Existing defense and detection techniques work well for specific attacks under various assumptions (e.g., the set of possible attacks are known beforehand).However, they are not sufficiently general to protect against a broader range of attacks.In this paper, we analyze the internals of DNN models under various attacks and identify two common exploitation channels: the provenance channel and the activation value distribution channel.We then propose a novel technique to extract DNN invariants and use them to perform runtime adversarial sample detection.Our experimental results of 11 different kinds of attacks on popular datasets including ImageNet and 13 models show that our technique can effectively detect all these attacks (over 90% accuracy) with limited false positives.We also compare it with three state-of-theart techniques including the Local Intrinsic Dimensionality (LID) based method, denoiser based methods (i.e., MagNet and HGD), and the prediction inconsistency based approach (i.e., feature squeezing).Our experiments show promising results.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Self-citationImageNet 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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
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
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
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
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
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317 · cited 3×
“In the gradient based approaches, attackers view generating an adversarial sample as an optimization problem and conduct gradient guided search to find adversarial samples [10, 22, 42, 60, 68] ( § II-C).”
BackgroundMethodThe Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Robust physical-world attacks on deep learning visual classification
Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00175 · Cited by 2,173
Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Athalye, A., Carlini, N., & Wagner, D. (2018) · arXiv · doi:10.48550/arxiv.1802.00420 · Cited by 2,172 · cited 1×
“Athalye et al. [3] also showed that hardening or obfuscating gradients can be circumvented by gradient approximation.”
BackgroundReluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Katz, G., Barrett, C., Dill, D. L., Julian, K., & Kochenderfer, M. J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63387-9_5 · Cited by 1,706
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Papernot, N., McDaniel, P., & Goodfellow, I. (2016) · arXiv · doi:10.48550/arxiv.1605.07277 · Cited by 1,326
Delving into Transferable Adversarial Examples and Black-box Attacks
Liu, Y., Chen, X., Liu, C., & Song, D. (2016) · arXiv · doi:10.48550/arxiv.1611.02770 · Cited by 1,310
Self-citationTrojaning Attack on Neural Networks
Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23291 · Cited by 1,270
Self-citationManipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
Jagielski, M., Oprea, A., Biggio, B., Liu, C., Nita-Rotaru, C., & Li, B. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00057 · Cited by 861
Stealing Machine Learning Models via Prediction APIs
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016) · arXiv · doi:10.48550/arxiv.1609.02943 · Cited by 796
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Song, Y., Kim, T., Nowozin, S., Ermon, S., & Kushman, N. (2017) · arXiv · doi:10.48550/arxiv.1710.10766 · Cited by 562 · cited 1×
“Defense techniques try to harden the NN models to prevent adversarial sample attacks [77, 86, 98].”
BackgroundMachine Learning Models that Remember Too Much
Song, C., Ristenpart, T., & Shmatikov, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134077 · Cited by 526 · cited 1×
“There are other types of attacks on machine learning models especially DNNs [27, 30, 82, 84, 85, 97].”
BackgroundBrown, T. B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017) · arXiv · doi:10.48550/arxiv.1712.09665 · Cited by 509
Machine Learning with Membership Privacy using Adversarial Regularization
Nasr, M., Shokri, R., & Houmansadr, A. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243855 · Cited by 458 · cited 1×
“Some works focus on studying the potential privacy leakage issues of machine learning [30, 37, 50, 62, 75, 84].”
BackgroundA general framework for adversarial examples with objectives
Sharif, M., Bhagavatula, S., Bauer, L., & Reiter, M. K. (2019) · ACM Transactions on Privacy and Security · doi:10.1145/3317611 · Cited by 200
Cited by
ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
Liu, Y., Lee, W.-C., Tao, G., Ma, S., Aafer, Y., & Zhang, X. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363216 · Cited by 404
Self-citationDataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Goldblum, M., Tsipras, D., Xie, C., Chen, X., Schwarzschild, A., Song, D., Madry, A., Li, B., & Goldstein, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3162397 · Cited by 362
“The detection algorithm NIC [136] approximates the distribution of neuron activation patterns and detects inputs that contain the trigger by comparing their activations to this approximate distribution.”
MethodRethinking the Backdoor Attacks’ Triggers: A Frequency Perspective
Zeng, Y., Park, W., Mao, Z. M., & Jia, R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01616 · Cited by 193
Deep learning library testing via effective model generation
Wang, Z., Yan, M., Chen, J., Liu, S., & Zhang, D. (2020) · Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3368089.3409761 · Cited by 167
“, testing DL models by generating adversarial inputs [48, 52, 66] or measuring the testing adequacy of DL models [45, 46, 55].”
MethodDeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
Wang, R., Juefei-Xu, F., Huang, Y., Guo, Q., Xie, X., Ma, L., & Liu, Y. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413716 · Cited by 131
“Monitoring neuron behaviors is an important technique for hunting the differences among a set of inputs to DNNs and investigating the internal behaviors of DNNs, which is widely employed in assuring the quality of DNNs [28, 35, 46, 60], protecting the safety of DNNs like fighting adversarial examples attack [30, 31],…”
MethodSelf-citation
Metadata
- Authors
- Ma, S., Liu, Y., Tao, G., Lee, W.-C., & Zhang, X.
- Venue
- Proceedings 2019 Network and Distributed System Security Symposium
- Publisher
- Internet Society
- Published
- 2019
- OpenAlex
- W2947133760
- Cited by
- 235
- References
- 31
- FWCI
- 12.82
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.