学習済み模倣方策はどれほど脆弱か?現代の行動クローニング方策に対する普遍的敵対的摂動攻撃
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
行動クローニング系の模倣学習アルゴリズム(Vanilla BC, LSTM-GMM, IBC, Diffusion Policy, VQ-BET)を対象に、ホワイトボックス・グレーボックス・ブラックボックスの敵対的攻撃への脆弱性を初めて体系的に比較評価した研究。
著者: Akansha Kalra, Basavasagar Patil, Guanhong Tao, Daniel S. Brown
分類: cs.LG, cs.CR, cs.RO
原文アブストラクト
Learning from demonstrations is a popular approach to train AI models; however, their vulnerability to adversarial attacks remains underexplored. We present the first systematic study of adversarial attacks, across a range of both classic and recently proposed imitation learning algorithms, including Vanilla Behavior Cloning (Vanilla BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and Vector-Quantized Behavior Transformer (VQ-BET). We study the vulnerability of these methods to both white-box, grey-box and black-box adversarial perturbations. Our experiments reveal that most existing methods are highly vulnerable to these attacks, including black-box transfer attacks that transfer across algorithms. To the best of our knowledge, we are the first to study and compare the vulnerabilities of different popular imitation learning algorithms to both white-box and black-box attacks. Our findings highlight the vulnerabilities of modern imitation learning algorithms, paving the way for future work in addressing such limitations. Videos and code are available at https://sites.google.com/view/uap-attacks-on-bc.
