English
Related papers

Related papers: Logit Pairing Methods Can Fool Gradient-Based Atta…

200 papers

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recently introduced direct alignment methods, which are often…

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

Computation and Language · Computer Science 2024-12-24 Yiyi Tao , Yixian Shen , Hang Zhang , Yanxin Shen , Lun Wang , Chuanqi Shi , Shaoshuai Du

In this technical report, we evaluate the adversarial robustness of a very recent method called "Geometry-aware Instance-reweighted Adversarial Training"[7]. GAIRAT reports state-of-the-art results on defenses to adversarial attacks on the…

Machine Learning · Computer Science 2021-03-08 Dorjan Hitaj , Giulio Pagnotta , Iacopo Masi , Luigi V. Mancini

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin

Modern neural networks are highly non-robust against adversarial manipulation. A significant amount of work has been invested in techniques to compute lower bounds on robustness through formal guarantees and to build provably robust models.…

Machine Learning · Computer Science 2019-09-26 Francesco Croce , Jonas Rauber , Matthias Hein

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that…

Machine Learning · Computer Science 2024-08-26 Zhenyu Liu , Haoran Duan , Huizhi Liang , Yang Long , Vaclav Snasel , Guiseppe Nicosia , Rajiv Ranjan , Varun Ojha

Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy. One approach to mitigate this trade-off is leveraging invariance regularization, which encourages model…

Machine Learning · Computer Science 2025-08-29 Futa Waseda , Ching-Chun Chang , Isao Echizen

In this paper, we propose a novel normalization method called penalty gradient normalization (PGN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as…

Computer Vision and Pattern Recognition · Computer Science 2023-06-26 Tian Xia

Mixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes locally linear constraints on the model's input space.…

Computation and Language · Computer Science 2021-09-16 Guang Liu , Yuzhao Mao , Hailong Huang , Weiguo Gao , Xuan Li

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

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"…

Machine Learning · Computer Science 2022-03-18 Alexander Levine , Soheil Feizi

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at…

Machine Learning · Computer Science 2018-06-07 Liang Tong , Sixie Yu , Scott Alfeld , Yevgeniy Vorobeychik

Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses…

Cryptography and Security · Computer Science 2023-01-02 Giovanni Apruzzese , Hyrum S. Anderson , Savino Dambra , David Freeman , Fabio Pierazzi , Kevin A. Roundy

Adversarial training, especially projected gradient descent (PGD), has proven to be a successful approach for improving robustness against adversarial attacks. After adversarial training, gradients of models with respect to their inputs…

Machine Learning · Statistics 2023-04-21 Ricardo Bigolin Lanfredi , Joyce D. Schroeder , Tolga Tasdizen

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Levente Halmosi , Mark Jelasity

Most existing works focus on improving robustness against adversarial attacks bounded by a single $l_p$ norm using adversarial training (AT). However, these AT models' multiple-norm robustness (union accuracy) is still low, which is crucial…

Machine Learning · Computer Science 2024-09-24 Enyi Jiang , Gagandeep Singh

Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations. Existing attack methods for k-nearest…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xiaodan Li , Yuefeng Chen , Yuan He , Hui Xue

Adversarial robust models have been shown to learn more robust and interpretable features than standard trained models. As shown in [\cite{tsipras2018robustness}], such robust models inherit useful interpretable properties where the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-05 Gunjan Aggarwal , Abhishek Sinha , Nupur Kumari , Mayank Singh

Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Xiaojun Jia , Yong Zhang , Baoyuan Wu , Ke Ma , Jue Wang , Xiaochun Cao

Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test…

Machine Learning · Computer Science 2019-12-20 Sanjam Garg , Somesh Jha , Saeed Mahloujifar , Mohammad Mahmoody