首次系统测试行为克隆模型对抗攻击脆弱性，发现多模型易受黑盒攻击。
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
- 用通用对抗扰动攻击多种行为克隆算法，涵盖白盒、灰盒和黑盒场景。
- 多数模型在黑盒攻击下性能下降超50%，且攻击可跨算法迁移。
- 适合关注强化学习安全性的研究人员与自动驾驶开发者参考。
从示范中学习是训练人工智能模型的流行方法，但其对对抗攻击的脆弱性尚未得到充分研究。本文首次系统地研究了多种经典及近期提出的模仿学习算法（包括基础行为克隆、LSTM-GMM、隐式行为克隆、扩散策略和向量量化行为变换器）在白盒、灰盒和黑盒对抗扰动下的脆弱性。实验表明，大多数现有方法极易受到这些攻击，包括可跨算法迁移的黑盒转移攻击。据我们所知，这是首个对比分析不同主流模仿学习算法在白盒与黑盒攻击下脆弱性的研究。结果揭示了现代模仿学习算法的安全隐患，为未来应对此类缺陷的研究提供了基础。视频与代码见 https://sites.google.com/view/uap-attacks-on-bc。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。