方法概述
Adversarial example detectors often fail when attackers explicitly attempt to bypass them. We propose a dual-model approach that keeps the original classifier fixed and trains a separate verifier to assess its predictions.
训练过程与激活签名
During training, we identify patterns of internal neural network activations that distinguish genuine examples of each class from adversarial examples targeting that class. These patterns, called activation signatures, guide the generation of challenging adversarial examples that mislead the classifier, challenge the verifier, and internally resemble the target class.
验证器训练与推理
The verifier learns to recognize these examples while preserving its performance on clean inputs through knowledge distillation. At inference, the verifier evaluates the classifier's prediction without requiring activation signatures.
实验评估与结果
We evaluate the approach on publicly available datasets against several adaptive attacks, including attacks unseen during training. The proposed verifier substantially outperforms directly attacked confidence-based and feature-based detectors under the evaluated L-infinity attacks.
Ablation studies show that adaptive verifier training is the main source of this improvement, while signature guidance primarily benefits clean accuracy. Additional L2 evaluations reveal limitations in robustness across perturbation types.