English
Related papers

Related papers: Is Certifying $\ell_p$ Robustness Still Worthwhile…

200 papers

Robustness against image perturbations bounded by a $\ell_p$ ball have been well-studied in recent literature. Perturbations in the real-world, however, rarely exhibit the pixel independence that $\ell_p$ threat models assume. A recently…

Machine Learning · Computer Science 2023-05-11 Edward J. Hu , Adith Swaminathan , Hadi Salman , Greg Yang

We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of…

Machine Learning · Statistics 2019-09-10 Dimitris Tsipras , Shibani Santurkar , Logan Engstrom , Alexander Turner , Aleksander Madry

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…

Machine Learning · Computer Science 2020-07-01 David Stutz , Matthias Hein , Bernt Schiele

Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Thomas Massena , Corentin Friedrich , Franck Mamalet , Mathieu Serrurier

Adaptive defenses, which optimize at test time, promise to improve adversarial robustness. We categorize such adaptive test-time defenses, explain their potential benefits and drawbacks, and evaluate a representative variety of the latest…

Machine Learning · Computer Science 2022-07-14 Francesco Croce , Sven Gowal , Thomas Brunner , Evan Shelhamer , Matthias Hein , Taylan Cemgil

The existence of adversarial examples poses a real danger when deep neural networks are deployed in the real world. The go-to strategy to quantify this vulnerability is to evaluate the model against specific attack algorithms. This approach…

Machine Learning · Computer Science 2021-06-08 Kevin Roth

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

Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often learn tasks in a similar order, we hypothesize that easier tasks will be easier regardless of…

Machine Learning · Computer Science 2026-02-04 Shir Ashury-Tahan , Ariel Gera , Elron Bandel , Michal Shmueli-Scheuer , Leshem Choshen

Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$)…

Machine Learning · Statistics 2025-01-22 Vaclav Voracek

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

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving…

Machine Learning · Computer Science 2025-12-23 Pierre-François Massiani , Alexander von Rohr , Lukas Haverbeck , Sebastian Trimpe

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the…

Machine Learning · Computer Science 2020-06-11 Shufei Zhang , Kaizhu Huang , Zenglin Xu

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we…

Cryptography and Security · Computer Science 2023-01-27 Hidde Lycklama , Lukas Burkhalter , Alexander Viand , Nicolas Küchler , Anwar Hithnawi

In safety-critical deep learning applications, robustness measures the ability of neural models that handle imperceptible perturbations in input data, which may lead to potential safety hazards. Existing pre-deployment robustness assessment…

Machine Learning · Computer Science 2025-08-27 Wenchuan Mu , Kwan Hui Lim

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 of robustness in…

Machine Learning · Computer Science 2018-11-21 Hajime Ono , Tsubasa Takahashi , Kazuya Kakizaki

Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the $\ell_p$-norm threat model of the input instances, robustness verification…

Machine Learning · Computer Science 2020-06-16 Jeet Mohapatra , Tsui-Wei , Weng , Pin-Yu Chen , Sijia Liu , Luca Daniel

Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which…

Machine Learning · Computer Science 2020-06-17 Yiming Li , Baoyuan Wu , Yan Feng , Yanbo Fan , Yong Jiang , Zhifeng Li , Shutao Xia

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

Adversarial training can considerably robustify deep neural networks to resist adversarial attacks. However, some works suggested that adversarial training might comprise the privacy-preserving and generalization abilities. This paper…

Machine Learning · Computer Science 2020-12-29 Fengxiang He , Shaopeng Fu , Bohan Wang , Dacheng Tao

The robustness of machine learning models has been questioned by the existence of adversarial examples. We examine the threat of adversarial examples in practical applications that require lightweight models for one-class classification.…

Machine Learning · Computer Science 2024-07-10 Matthew Lau , Haoran Wang , Alec Helbling , Matthew Hul , ShengYun Peng , Martin Andreoni , Willian T. Lunardi , Wenke Lee