Provable Adversarial Robustness for Fractional Lp Threat Models

In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms" (quasi-norms defined by the L_p distance with 0

cs.LG cs.CR Adversarial Robustness in Machine Learning Computer Science Mathematics

View graph Source

Paper

Similar papers

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$Francesco Croce, Matthias Hein2019 · International Conference on Learning Representations · 80 citations In Library

Adversarial Robustness Assessment: Why both $L_0$ and $L_\infty$ Attacks Are NecessaryShashank Kotyan, Danilo Vasconcellos Vargas2019 · arXiv: Learning · 20 citations In Library

Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust ClassifiersFrancesco Croce, Matthias Hein2021 · arXiv (Cornell University) · 29 citations In Library

Adversarial robustness assessment: Why in evaluation both L0 and L∞ attacks are necessaryShashank Kotyan, Danilo Vasconcellos Vargas2022 · PLoS ONE · 31 citations In Library

Provable Robustness against a Union of L_0 Adversarial AttacksZayd Hammoudeh, Daniel Lowd2024 · Proceedings of the AAAI Conference on Artificial Intelligence In Library

Provable Adversarial Robustness in the Quantum ModelKhashayar Barooti, Grzegorz Gluch, R. Urbanke2021 · arXiv.org · 2 citations In Library

Toward Efficient Robust Training against Union of $\ell_p$ Threat ModelsGaurang Sriramanan, Maharshi Gor, S. Feizi2022 · Neural Information Processing Systems · 2 citations In Library

On Norm-Agnostic Robustness of Adversarial TrainingBai Li, Changyou Chen, Wenlin Wang et al.2019 · arXiv.org · 8 citations In Library

A Closer Look at Robustness to L-infinity and Spatial Perturbations and their CompositionLuke Rowe, Benjamin Therien, Krzysztof Czarnecki et al.2022 · arXiv (Cornell University) In Library

Optimising Network Architectures for Provable Adversarial RobustnessHenry Gouk, Timothy M. Hospedales2020 · 2020 Sensor Signal Processing for Defence Conference (SSPD) · 2 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal