paper-with-me

Papers

Provable Adversarial Robustness for Fractional Lp Threat Models

2022-03-16 · Alexander Levine, Soheil Feizi

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<p<1) have yet to be thoroughly considered. We proactively propose a defense with several desirable properties: it provides provable (certified) robustness, scales to ImageNet, and yields deterministic (rather than high-probability) certified guarantees when applied to quantized data (e.g., images). Our technique for fractional L_p robustness constructs expressive, deep classifiers that are globally Lipschitz with respect to the L_p^p metric, for any 0<p<1. However, our method is even more general: we can construct classifiers which are globally Lipschitz with respect to any metric defined as the sum of concave functions of components. Our approach builds on a recent work, Levine and Feizi (2021), which provides a provable defense against L_1 attacks. However, we demonstrate that our proposed guarantees are highly non-vacuous, compared to the trivial solution of using (Levine and Feizi, 2021) directly and applying norm inequalities. Code is available at https://github.com/alevine0/fractionalLpRobustness.

📄 PDF Abstract BibTeX arXiv:2203.08945

Code (1)

alevine0/fractionallprobustness 공식 구현 pytorch

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Optimising Neural Network Architectures for Provable Adversarial Robustness

2020-01-01 · ICLR 2020 1 · Henry Gouk, Timothy M. Hospedales

Existing Lipschitz-based provable defences to adversarial examples only cover the L2 threat model. We introduce the first bound that makes use of Lipschitz continuity to provide a more general guarantee for threat models…

Adversarial Robustness

Evaluating robustness of support vector machines with the Lagrangian dual approach

2023-06-05 · YuTing Liu, Hong Gu, Pan Qin

Adversarial examples bring a considerable security threat to support vector machines (SVMs), especially those used in safety-critical applications. Thus, robustness verification is an essential issue for SVMs, which can …

Adversarial Robustness

PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches

2021-04-26 · Chong Xiang, Prateek Mittal

An adversarial patch can arbitrarily manipulate image pixels within a restricted region to induce model misclassification. The threat of this localized attack has gained significant attention because the adversary can mo…

PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking

2020-05-17 · Chong Xiang, Arjun Nitin Bhagoji, Vikash Sehwag, Prateek Mittal

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attac…

Lyapunov Stable Graph Neural Flow

2026-03-13 · Haoyu Chu, Xiaotong Chen, Wei Zhou, Wenjun Cui 외 arxiv

Graph Neural Networks (GNNs) are highly vulnerable to adversarial perturbations in both topology and features, making the learning of robust representations a critical challenge. In this work, we bridge GNNs with control…

Adversarial Attack