Adversarial Attacks Leverage Interference Between Features in Superposition
对抗攻击利用特征叠加中的干扰
机构 * Department of Computer Science, Imperial College London, London, United Kingdom(帝国理工学院伦敦校区计算机科学系)
AI总结 本文揭示神经网络中特征叠加导致的干扰是对抗脆弱性的根源,通过理论推导和实验验证了干扰模式决定攻击成功与迁移性。
Comments Forty-third International Conference on Machine Learning