English
Related papers

Related papers: UniCR: Universally Approximated Certified Robustne…

200 papers

Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers…

Machine Learning · Computer Science 2024-05-24 Ambar Pal , René Vidal , Jeremias Sulam

Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers. While randomized smoothing typically yields robust $\ell_2$-ball certificates, recent research has generalized provable robustness to…

Machine Learning · Computer Science 2023-09-26 Samuel Pfrommer , Brendon G. Anderson , Somayeh Sojoudi

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious…

Software Engineering · Computer Science 2024-05-14 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , Bo Jiang , W. K. Chan

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…

Cryptography and Security · Computer Science 2024-05-02 Daniel Gibert , Luca Demetrio , Giulio Zizzo , Quan Le , Jordi Planes , Battista Biggio

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

Machine Learning · Computer Science 2019-01-08 Tsui-Wei Weng , Pin-Yu Chen , Lam M. Nguyen , Mark S. Squillante , Ivan Oseledets , Luca Daniel

Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to adversarial attacks, as even minor meaning-preserving changes…

Machine Learning · Computer Science 2025-12-11 Zixia Wang , Gaojie Jin , Jia Hu , Ronghui Mu

Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety. Current robustness certificates for graph classifiers guarantee output invariance with respect to the total number of node pair flips…

Machine Learning · Computer Science 2023-06-27 Pierre Osselin , Henry Kenlay , Xiaowen Dong

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base…

Machine Learning · Computer Science 2019-11-22 Alexander Levine , Soheil Feizi

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

Machine Learning · Computer Science 2022-03-09 Maria-Florina Balcan , Avrim Blum , Steve Hanneke , Dravyansh Sharma

Deployed language models must decide not only what to answer but also when not to answer. We present UniCR, a unified framework that turns heterogeneous uncertainty evidence including sequence likelihoods, self-consistency dispersion,…

Computation and Language · Computer Science 2025-12-30 Markus Oehri , Giulia Conti , Kaviraj Pather , Alexandre Rossi , Laia Serra , Adrian Parody , Rogvi Johannesen , Aviaja Petersen , Arben Krasniqi

Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal…

Machine Learning · Computer Science 2026-05-14 Blaise Delattre , Hengyu Wu , Paul Caillon , Wei Yang Bryan Lim , Yang Cao

A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably…

Machine Learning · Computer Science 2021-01-21 Mengting Xu , Tao Zhang , Zhongnian Li , Daoqiang Zhang

Several recent results provide theoretical insights into the phenomena of adversarial examples. Existing results, however, are often limited due to a gap between the simplicity of the models studied and the complexity of those deployed in…

Machine Learning · Computer Science 2021-01-05 Jeremias Sulam , Ramchandran Muthukumar , Raman Arora

Recent papers have demonstrated that ensemble stumps and trees could be vulnerable to small input perturbations, so robustness verification and defense for those models have become an important research problem. However, due to the…

Machine Learning · Computer Science 2020-09-30 Yihan Wang , Huan Zhang , Hongge Chen , Duane Boning , Cho-Jui Hsieh

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial or worst-case inputs, but researchers…

Machine Learning · Computer Science 2023-01-26 Brendon G. Anderson , Somayeh Sojoudi

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

Machine Learning · Computer Science 2021-03-31 Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Jihun Hamm

Randomized smoothing has shown promising certified robustness against adversaries in classification tasks. Despite such success with only zeroth-order access to base models, randomized smoothing has not been extended to a general form of…

Machine Learning · Computer Science 2024-05-16 Aref Miri Rekavandi , Olga Ohrimenko , Benjamin I. P. Rubinstein

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Computation and Language · Computer Science 2021-07-27 Jiehang Zeng , Xiaoqing Zheng , Jianhan Xu , Linyang Li , Liping Yuan , Xuanjing Huang

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against…

Cryptography and Security · Computer Science 2020-07-21 Binghui Wang , Xiaoyu Cao , Jinyuan jia , Neil Zhenqiang Gong

Currently the most popular method of providing robustness certificates is randomized smoothing where an input is smoothed via some probability distribution. We propose a novel approach to randomized smoothing over multiplicative parameters.…

Machine Learning · Computer Science 2022-08-17 Nikita Muravev , Aleksandr Petiushko