paper-with-me

홈 › Papers

General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing

2023-08-17 · Dmitrii Korzh, Mikhail Pautov, Olga Tsymboi, Ivan Oseledets

Randomized smoothing is the state-of-the-art approach to construct image classifiers that are provably robust against additive adversarial perturbations of bounded magnitude. However, it is more complicated to construct reasonable certificates against semantic transformation (e.g., image blurring, translation, gamma correction) and their compositions. In this work, we propose \emph{General Lipschitz (GL),} a new framework to certify neural networks against composable resolvable semantic perturbations. Within the framework, we analyze transformation-dependent Lipschitz-continuity of smoothed classifiers w.r.t. transformation parameters and derive corresponding robustness certificates. Our method performs comparably to state-of-the-art approaches on the ImageNet dataset.

📄 PDF Abstract BibTeX arXiv:2309.16710

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Lightweight Lipschitz Margin Training for Certified Defense against Adversarial Examples

2018-11-20 · Hajime Ono, Tsubasa Takahashi, Kazuya Kakizaki

How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\epsilon$-robust, consume huge resources, they can only achieve small degree…

TSS: Transformation-Specific Smoothing for Robustness Certification

2020-02-27 · Linyi Li, Maurice Weber, Xiaojun Xu, Luka Rimanic 외

As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislead ML systems by perturbing test data usi…

Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective

2022-10-04 · Bohang Zhang, Du Jiang, Di He, LiWei Wang

Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples. However, the relevant progress for the important $\ell_\infty$ perturbat…

Robust classification

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

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…