行動クローニング方策に対するデータセット汚染攻撃
Dataset Poisoning Attacks on Behavioral Cloning Policies
行動クローニングの方策がクリーンラベルバックドア攻撃に脆弱であることを初めて示し、汚染率やトリガー強度による影響と、エントロピーに基づく新たなテスト時トリガー攻撃を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Akansha Kalra, Soumil Datta, Ethan Gilmore, Duc La, Guanhong Tao, Daniel S. Brown
分類: cs.LG, cs.CR, cs.RO
原文アブストラクト
Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential vulnerabilities are an important concern. In this work, we perform the first analysis of the efficacy of clean-label backdoor attacks on BC policies. Our backdoor attacks poison a dataset of demonstrations by injecting a visual trigger to create a spurious correlation that can be exploited at test time. We evaluate how policy vulnerability scales with the fraction of poisoned data, the strength of the trigger, and the trigger type. We also introduce a novel entropy-based test-time trigger attack that substantially degrades policy performance by identifying critical states where test-time triggering of the backdoor is expected to be most effective at degrading performance. We empirically demonstrate that BC policies trained on even minimally poisoned datasets exhibit deceptively high, near-baseline task performance despite being highly vulnerable to backdoor trigger attacks during deployment. Our results underscore the urgent need for more research into the robustness of BC policies, particularly as large-scale datasets are increasingly used to train policies for real-world cyber-physical systems. Videos and code are available at https://sites.google.com/view/dataset-poisoning-in-bc.
