ACL Findings2022
Input-specific Attention Subnetworks for Adversarial Detection
Emil Biju, Anirudh Sriram, Pratyush Kumar, Mitesh M. Khapra
Abstract
Self-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning. In this work, we demonstrate an altogether different utility of attention heads, namely for adversarial detection. Specifically, we propose a method to construct input-specific attention subnetworks (IAS) from which we extract three features to discriminate between authentic and adversarial inputs. The resultant detector significantly improves (by over 7.5%) the state-of-the-art adversarial detection accuracy for the BERT encoder on 10 NLU datasets with 11 different adversarial attack types. We also demonstrate that our method (a) is more accurate for larger models which are likely to have more spurious correlations and thus vulnerable to adversarial attack, and (b) performs well even with modest training sets of adversarial examples.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
- ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty EstimationFan Yin, Yao Li, Cho-Jui Hsieh, Kai-Wei ChangEMNLP 2022 · 6 citations
- Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language GenerationZhen Lin, Shubhendu Trivedi, Jimeng SunEMNLP 2024 · 1 citation
Builds on4
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable FeaturesSangdoo Yun, Dongyoon Han, Sanghyuk Chun, Seong Joon Oh et al.ICCV 2019 · 5,843 citations
- TinyBERT: Distilling BERT for Natural Language UnderstandingXiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang et al.EMNLP Findings 2020 · 1,787 citations
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, Peter SzolovitsAAAI 2020 · 1,333 citations
- The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERTMadhura Pande, Aakriti Budhraja, Preksha Nema, Pratyush Kumar et al.AAAI 2021 · 21 citations
Related papers
- Self-Attention Attribution: Interpreting Information Interactions Inside TransformerYaru Hao, Li Dong, Furu Wei, Ke XuAAAI 2021 · 282 citations
- Adversarial Self-Attention for Language UnderstandingHongqiu Wu, Ruixue Ding, Hai Zhao, Pengjun Xie et al.AAAI 2023 · 19 citations
- Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient DirectionsYuhang Wu, Sunpreet S. Arora, Yanhong Wu, Hao YangAAAI 2021 · 12 citations
- Adversarial Example Detection Using Latent Neighborhood GraphAhmed Abusnaina, Yuhang Wu, Sunpreet S. Arora, Yizhen Wang et al.ICCV 2021 · 70 citations
- Artificial Text Detection via Examining the Topology of Attention MapsLaida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova et al.EMNLP 2021 · 27 citations
