English
Related papers

Related papers: Two Coupled Rejection Metrics Can Tell Adversarial…

200 papers

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

Machine Learning · Computer Science 2020-10-23 Akhilan Boopathy , Sijia Liu , Gaoyuan Zhang , Cynthia Liu , Pin-Yu Chen , Shiyu Chang , Luca Daniel

Deep neural classifiers have recently found tremendous success in data-driven control systems. However, existing models suffer from a trade-off between accuracy and adversarial robustness. This limitation must be overcome in the control of…

Machine Learning · Computer Science 2024-06-05 Yatong Bai , Brendon G. Anderson , Somayeh Sojoudi

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Machine Learning · Computer Science 2021-06-03 Omer Faruk Tuna , Ferhat Ozgur Catak , M. Taner Eskil

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Sylvestre-Alvise Rebuffi , Sven Gowal , Dan A. Calian , Florian Stimberg , Olivia Wiles , Timothy Mann

We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier…

Machine Learning · Computer Science 2018-12-18 Kevin Eykholt , Atul Prakash

Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step attacks incur significant computational overhead, single-step variants are…

Machine Learning · Computer Science 2025-03-25 Alessandro De Palma , Serge Durand , Zakaria Chihani , François Terrier , Caterina Urban

We present a reinforcement learning (RL) framework in which the learned policy comes with a machine-checkable certificate of provable adversarial robustness. Our approach, called CAROL, learns a model of the environment. In each learning…

Machine Learning · Computer Science 2023-05-30 Chenxi Yang , Greg Anderson , Swarat Chaudhuri

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…

Artificial Intelligence · Computer Science 2026-01-12 Can Xu , Lingyong Yan , Jiayi Wu , Haosen Wang , Shuaiqiang Wang , Yuchen Li , Jizhou Huang , Dawei Yin , Xiang Li

While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. Defenses based on regularization and adversarial training are…

Machine Learning · Computer Science 2019-02-07 Sahil Singla , Soheil Feizi

We are proposing to use an ensemble of diverse specialists, where speciality is defined according to the confusion matrix. Indeed, we observed that for adversarial instances originating from a given class, labeling tend to be done into a…

Neural and Evolutionary Computing · Computer Science 2017-03-13 Mahdieh Abbasi , Christian Gagné

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Machine Learning · Computer Science 2021-05-26 Leo Schwinn , René Raab , An Nguyen , Dario Zanca , Bjoern Eskofier

Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts. They are a natural choice to solve discriminative tasks in a robust manner as they jointly optimize for predictive…

Machine Learning · Computer Science 2020-02-18 Ethan Fetaya , Jörn-Henrik Jacobsen , Will Grathwohl , Richard Zemel

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

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

Machine Learning · Computer Science 2022-06-24 Haojing Shen , Sihong Chen , Ran Wang , Xizhao Wang

Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised…

Cryptography and Security · Computer Science 2018-08-20 Ziyi Bao , Luis Muñoz-González , Emil C. Lupu

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Machine Learning · Computer Science 2019-10-18 Yogesh Balaji , Tom Goldstein , Judy Hoffman

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

Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the models into predicting incorrect classes. Our study of major…

Cryptography and Security · Computer Science 2023-06-02 Mohammed Alkhowaiter , Hisham Kholidy , Mnassar Alyami , Abdulmajeed Alghamdi , Cliff Zou

In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is $\|F({\bf x})\|_\infty$ (i.e. how…

Machine Learning · Computer Science 2018-10-16 Xi Wu , Uyeong Jang , Jiefeng Chen , Lingjiao Chen , Somesh Jha