Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (10) , 10825-10833
Abstract
Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by adversarial perturbation and lead to an unexpectedly increasing gap between features in the last hidden layer of natural and adversarial samples. To address this issue, we propose a disentanglement-based approach to explicitly model and further remove the specific latent features. We introduce a feature disentangler to separate out the specific latent features from the features of the adversarial samples, thereby boosting robustness by eliminating the specific latent features. Besides, we align clean features in the pre-trained model with features of adversarial samples in the fine-tuned model, to benefit from the intrinsic features of natural samples. Empirical evaluations on three benchmark datasets demonstrate that our approach surpasses existing adversarial fine-tuning methods and adversarial training baselines.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Inspector for Face Forgery Detection: Defending Against Adversarial Attacks From Coarse to FineIEEE Transactions on Image Processing, 2024
- Physical Adversarial Attack Meets Computer Vision: A Decade SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Fast Adversarial Training With Adaptive Step SizeIEEE Transactions on Image Processing, 2023
- Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff2023
- Robust Evaluation of Diffusion-Based Adversarial Purification2023
- Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning2021
- Wide Residual Networks2016