Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

Zhiyuan He, Yijun Yang, Pin-Yu Chen, Qiang Xu, Tsung-Yi Ho
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18063-18080, 2024.

Abstract

Deep Neural Networks (DNNs) are vulnerable to Adversarial Examples (AEs), hindering their use in safety-critical systems. In this paper, we present BEYOND, an innovative AE detection framework designed for reliable predictions. BEYOND identifies AEs by distinguishing the AE’s abnormal relation with its augmented versions, i.e. neighbors, from two prospects: representation similarity and label consistency. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label for its highly informative representation capacity compared to supervised learning models. We found clean samples maintain a high degree of representation similarity and label consistency relative to their neighbors, in contrast to AEs which exhibit significant discrepancies. We explain this observation and show that leveraging this discrepancy BEYOND can accurately detect AEs. Additionally, we develop a rigorous justification for the effectiveness of BEYOND. Furthermore, as a plug-and-play model, BEYOND can easily cooperate with the Adversarial Trained Classifier (ATC), achieving state-of-the-art (SOTA) robustness accuracy. Experimental results show that BEYOND outperforms baselines by a large margin, especially under adaptive attacks. Empowered by the robust relationship built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed. Project page: https://huggingface.co/spaces/allenhzy/Be-Your-Own-Neighborhood.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-he24l, title = {Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning}, author = {He, Zhiyuan and Yang, Yijun and Chen, Pin-Yu and Xu, Qiang and Ho, Tsung-Yi}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {18063--18080}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/he24l/he24l.pdf}, url = {https://proceedings.mlr.press/v235/he24l.html}, abstract = {Deep Neural Networks (DNNs) are vulnerable to Adversarial Examples (AEs), hindering their use in safety-critical systems. In this paper, we present BEYOND, an innovative AE detection framework designed for reliable predictions. BEYOND identifies AEs by distinguishing the AE’s abnormal relation with its augmented versions, i.e. neighbors, from two prospects: representation similarity and label consistency. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label for its highly informative representation capacity compared to supervised learning models. We found clean samples maintain a high degree of representation similarity and label consistency relative to their neighbors, in contrast to AEs which exhibit significant discrepancies. We explain this observation and show that leveraging this discrepancy BEYOND can accurately detect AEs. Additionally, we develop a rigorous justification for the effectiveness of BEYOND. Furthermore, as a plug-and-play model, BEYOND can easily cooperate with the Adversarial Trained Classifier (ATC), achieving state-of-the-art (SOTA) robustness accuracy. Experimental results show that BEYOND outperforms baselines by a large margin, especially under adaptive attacks. Empowered by the robust relationship built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed. Project page: https://huggingface.co/spaces/allenhzy/Be-Your-Own-Neighborhood.} }
Endnote
%0 Conference Paper %T Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning %A Zhiyuan He %A Yijun Yang %A Pin-Yu Chen %A Qiang Xu %A Tsung-Yi Ho %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-he24l %I PMLR %P 18063--18080 %U https://proceedings.mlr.press/v235/he24l.html %V 235 %X Deep Neural Networks (DNNs) are vulnerable to Adversarial Examples (AEs), hindering their use in safety-critical systems. In this paper, we present BEYOND, an innovative AE detection framework designed for reliable predictions. BEYOND identifies AEs by distinguishing the AE’s abnormal relation with its augmented versions, i.e. neighbors, from two prospects: representation similarity and label consistency. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label for its highly informative representation capacity compared to supervised learning models. We found clean samples maintain a high degree of representation similarity and label consistency relative to their neighbors, in contrast to AEs which exhibit significant discrepancies. We explain this observation and show that leveraging this discrepancy BEYOND can accurately detect AEs. Additionally, we develop a rigorous justification for the effectiveness of BEYOND. Furthermore, as a plug-and-play model, BEYOND can easily cooperate with the Adversarial Trained Classifier (ATC), achieving state-of-the-art (SOTA) robustness accuracy. Experimental results show that BEYOND outperforms baselines by a large margin, especially under adaptive attacks. Empowered by the robust relationship built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed. Project page: https://huggingface.co/spaces/allenhzy/Be-Your-Own-Neighborhood.
APA
He, Z., Yang, Y., Chen, P., Xu, Q. & Ho, T.. (2024). Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:18063-18080 Available from https://proceedings.mlr.press/v235/he24l.html.

Related Material