English
Related papers

Related papers: Closing the Gap: Achieving Better Accuracy-Robustn…

200 papers

The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symmetry-Breaking Dimensional Expansion (SBDE) as a controlled…

Machine Learning · Computer Science 2026-02-23 Yu Bai , Zhe Wang , Jiarui Zhang , Dong-Xiao Zhang , Yinjun Gao , Jun-Jie Zhang

Adversarial attacks based on randomized search schemes have obtained state-of-the-art results in black-box robustness evaluation recently. However, as we demonstrate in this work, their efficiency in different query budget regimes depends…

Machine Learning · Computer Science 2021-11-23 Maksym Yatsura , Jan Hendrik Metzen , Matthias Hein

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Cryptography and Security · Computer Science 2021-03-16 Zhe Zhao , Guangke Chen , Jingyi Wang , Yiwei Yang , Fu Song , Jun Sun

This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (\emph{i.e.} classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of…

Machine Learning · Computer Science 2021-02-23 Rafael Pinot , Laurent Meunier , Florian Yger , Cédric Gouy-Pailler , Yann Chevaleyre , Jamal Atif

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

Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as a mitigation where given an input $\mathbf{x}$, a…

Cryptography and Security · Computer Science 2024-09-10 Jiankai Jin , Olga Ohrimenko , Benjamin I. P. Rubinstein

Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calculated size. While there is value in these certifications, the…

Machine Learning · Computer Science 2023-09-21 Andrew C. Cullen , Paul Montague , Shijie Liu , Sarah M. Erfani , Benjamin I. P. Rubinstein

Adversarial training improves the robustness of neural networks against adversarial attacks, albeit at the expense of the trade-off between standard and robust generalization. To unveil the underlying factors driving this phenomenon, we…

Machine Learning · Computer Science 2024-01-29 Shruthi Gowda , Bahram Zonooz , Elahe Arani

The query-based black-box attacks have raised serious threats to machine learning models in many real applications. In this work, we study a lightweight defense method, dubbed Random Noise Defense (RND), which adds proper Gaussian noise to…

Machine Learning · Computer Science 2021-11-02 Zeyu Qin , Yanbo Fan , Hongyuan Zha , Baoyuan Wu

Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to…

Machine Learning · Computer Science 2023-04-11 Xunyu Zhu , Jian Li , Yong Liu , Weiping Wang

Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional trained classifier to detect and correct the adversarial samples,…

Machine Learning · Computer Science 2024-08-26 Anurag Singh , Mahalakshmi Sabanayagam , Krikamol Muandet , Debarghya Ghoshdastidar

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Machine Learning · Computer Science 2023-09-06 Ruihan Zhang , Peixin Zhang , Jun Sun

Cyber attacks continue to be a cause of concern despite advances in cyber defense techniques. Although cyber attacks cannot be fully prevented, standard decision-making frameworks typically focus on how to prevent them from succeeding,…

Systems and Control · Electrical Eng. & Systems 2025-09-16 Faezeh Shojaeighadikolaei , Shouhuai Xu , Keith Paarporn

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…

Machine Learning · Computer Science 2019-03-18 Ian Goodfellow

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li

Certified robustness guarantee gauges a model's robustness to test-time attacks and can assess the model's readiness for deployment in the real world. In this work, we critically examine how the adversarial robustness guarantees from…

Machine Learning · Computer Science 2021-12-02 Jiachen Sun , Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Dan Hendrycks , Jihun Hamm , Z. Morley Mao

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

Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consistently. Here, we propose to use adversarial attacks as a…

Neural and Evolutionary Computing · Computer Science 2021-06-11 Shashank Kotyan , Danilo Vasconcellos Vargas

Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we…

Machine Learning · Computer Science 2021-01-11 Alexander Levine , Soheil Feizi