Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
원문 초록
Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model invariance under adversarial perturbations; however, it still leads to accuracy loss. In this work, we closely analyze the challenges of using invariance regularization in adversarial training and understand how to address them. Our analysis identifies two key issues: (1) a ``gradient conflict" between invariance and classification objectives, leading to suboptimal convergence, and (2) the mixture distribution problem arising from diverged distributions between clean and adversarial inputs. To address these issues, we propose Asymmetric Representation-regularized Adversarial Training (ARAT), which incorporates asymmetric invariance loss with stop-gradient operation and a predictor to avoid gradient conflict, and a split-BatchNorm (BN) structure to resolve the mixture distribution problem. Our detailed analysis demonstrates that each component effectively addresses the identified issues, offering novel insights into adversarial defense. ARAT shows superiority over existing methods across various settings. Finally, we discuss the implications of our findings to knowledge distillation-based defenses, providing a new perspective on their relative successes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
ShapeEmbed: a self-supervised learning framework for 2D contour quantification
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing
USAD: Universal Speech and Audio Representation via Distillation
Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.