Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks
Deep neural networks and Vision Transformers achieve state-of-the-art performance in computer vision but are highly vulnerable to adversarial perturbations. Standard defenses often incur high computational cost or lack formal guarantees. We propose a Lipschitz-guided stochastic depth (DropPath) method, where drop probabilities increase with depth to control the effective Lipschitz constant of the network. This approach regularizes deeper layers, improving robustness while preserving clean accuracy and reducing computation. Experiments on CIFAR-10 with ViT-Tiny show that our custom depth-dependent schedule maintains near-baseline clean accuracy, enhances robustness under FGSM, PGD-20, and AutoAttack, and significantly reduces FLOPs compared to baseline and linear DropPath schedules.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity
We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robustness under L2 certificates and empirical robustness against strong L…
Adversarial RobustnessAdversarial DefenseExposing and Defending the Achilles' Heel of Video Mixture-of-Experts
Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often treat MoE as a unified architecture, overlook…
Adversarial RobustnessLipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Co…
Robust Object DetectionAdversarial RobustnessALMA: Aggregated Lipschitz Maximization Attack on Auto-encoders
Despite the extensive use of deep autoencoders (AEs) in critical applications, their adversarial robustness remains relatively underexplored compared to classification models. AE robustness is characterized by the Lipsch…
Adversarial RobustnessLipschitz-aware Linearity Grafting for Certified Robustness
Lipschitz constant is a fundamental property in certified robustness, as smaller values imply robustness to adversarial examples when a model is confident in its prediction. However, identifying the worst-case adversaria…