Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
Despite the significant advances that deep neural networks (DNNs) have achieved in various visual tasks, they still exhibit vulnerability to adversarial examples, leading to serious security concerns. Recent adversarial training techniques have utilized inverse adversarial attacks to generate high-confidence examples, aiming to align the distributions of adversarial examples with the high-confidence regions of their corresponding classes. However, in this paper, our investigation reveals that high-confidence outputs under inverse adversarial attacks are correlated with biased feature activation. Specifically, training with inverse adversarial examples causes the model's attention to shift towards background features, introducing a spurious correlation bias. To address this bias, we propose Debiased High-Confidence Adversarial Training (DHAT), a novel approach that not only aligns the logits of adversarial examples with debiased high-confidence logits obtained from inverse adversarial examples, but also restores the model's attention to its normal state by enhancing foreground logit orthogonality. Extensive experiments demonstrate that DHAT achieves state-of-the-art performance and exhibits robust generalization capabilities across various vision datasets. Additionally, DHAT can seamlessly integrate with existing advanced adversarial training techniques for improving the performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks
Adversarial defenses train deep neural networks to be invariant to the input perturbations from adversarial attacks. Almost all defense strategies achieve this invariance through adversarial training i.e. training on inp…
Adversarial RobustnessCalibrating Uncertainty for Zero-Shot Adversarial CLIP
CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks. Prior adversarial fine-tuning work primarily matches predicted logits between clean and adversarial examples, which over…
Zero-shot GeneralizationAdversarial RobustnessConstraining Logits by Bounded Function for Adversarial Robustness
We propose a method for improving adversarial robustness by addition of a new bounded function just before softmax. Recent studies hypothesize that small logits (inputs of softmax) by logit regularization can improve adv…
Adversarial RobustnessLogit Pairing Methods Can Fool Gradient-Based Attacks
Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) an…
Adversarial RobustnessMixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with a…
Adversarial RobustnessRobust classification