paper-with-me

홈 › Papers

Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks

2025-09-12 · Laith Nayal, Mahmoud Mousatat, Bader Rasheed arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.10298

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity

2026-05-02 · Joy Dhar, Song Xia, Manish Kumar Pandey, Maryam Haghighat 외 arxiv

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 Defense

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts

2026-02-01 · Songping Wang, Qinglong Liu, Yueming Lyu, Ning Li 외 arxiv

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 Robustness

LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection

2026-07-06 · Vincent Lébé, Yannick Prudent, Corentin Friedrich, Thomas Massena 외 arxiv

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 Robustness

ALMA: Aggregated Lipschitz Maximization Attack on Auto-encoders

2025-05-06 · Chethan Krishnamurthy Ramanaik, Arjun Roy, Eirini Ntoutsi

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 Robustness

Lipschitz-aware Linearity Grafting for Certified Robustness

2025-10-29 · Yongjin Han, Suhyun Kim arxiv

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…