cs.LGNov 18, 2026

Learning to Verify: Signature-Guided Training for Adaptive Adversarial Detection

Authors: Arash Vashagh, Roozbeh Razavi-Far

Organizations: Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Fredericton, NB, Canada

Abstract

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. 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. 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. 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.

Figures & tables

Explore similar work

CardsList
  1. Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification

    Oct 11, 2026Rui Zhang, Youwen Zhu, Xinle Cao +2Adversarial Example DetectionAdversarial Robustness

  2. A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection

    May 19, 2025Sanggeon Yun, Ryozo Masukawa, Hyunwoo Oh +2Adversarial AttacksAdversarial Examples

  3. GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks

    Oct 7, 2026Arash Vashagh, Roozbeh Razavi-FarAdversarial Example DetectionAdversarial Attacks