English
Related papers

Related papers: Lightweight Lipschitz Margin Training for Certifie…

200 papers

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

Machine Learning · Computer Science 2026-05-27 Kevin Kuo , Chhavi Yadav , Virginia Smith

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Machine Learning · Computer Science 2026-04-15 Shaopeng Fu , Di Wang

The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-the-art defense…

Machine Learning · Computer Science 2022-08-02 Jay Nandy , Sudipan Saha , Wynne Hsu , Mong Li Lee , Xiao Xiang Zhu

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured…

Machine Learning · Computer Science 2022-01-13 Aounon Kumar , Tom Goldstein

In this work we propose a graph-based learning framework to train models with provable robustness to adversarial perturbations. In contrast to regularization-based approaches, we formulate the adversarially robust learning problem as one of…

Machine Learning · Computer Science 2020-10-26 Vishaal Krishnan , Abed AlRahman Al Makdah , Fabio Pasqualetti

Federated Learning (FL) facilitates collaborative model training among distributed clients while ensuring that raw data remains on local devices.Despite this advantage, FL systems are still exposed to risks from malicious or unreliable…

Cryptography and Security · Computer Science 2026-01-30 Deepthy K Bhaskar , Minimol B , Binu V P

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

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose Manifold-Constrained…

Machine Learning · Computer Science 2026-05-05 Guanmeng Xian , Ning Yang , Philip S. Yu

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an "attack"…

Machine Learning · Computer Science 2020-12-23 Minhao Cheng , Pin-Yu Chen , Sijia Liu , Shiyu Chang , Cho-Jui Hsieh , Payel Das

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training problem as a joint optimization problem with both empirical…

Machine Learning · Computer Science 2021-06-08 Jiameng Fan , Wenchao Li

Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustness of the…

Machine Learning · Computer Science 2021-07-02 Fan Liu , Shuyu Zhao , Xuelong Dai , Bin Xiao

Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…

Machine Learning · Computer Science 2020-10-27 Huimin Zeng , Chen Zhu , Tom Goldstein , Furong Huang

Neural networks are getting better accuracy with higher energy and computational cost. After quantization, the cost can be greatly saved, and the quantized models are more hardware friendly with acceptable accuracy loss. On the other hand,…

Machine Learning · Computer Science 2021-10-26 Chang Song , Riya Ranjan , Hai Li

Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We introduce \emph{LipNeXt}, the first \emph{constraint-free} and…

Machine Learning · Computer Science 2026-01-27 Kai Hu , Haoqi Hu , Matt Fredrikson

We study adversarial robustness of neural networks from a margin maximization perspective, where margins are defined as the distances from inputs to a classifier's decision boundary. Our study shows that maximizing margins can be achieved…

Machine Learning · Computer Science 2020-03-06 Gavin Weiguang Ding , Yash Sharma , Kry Yik Chau Lui , Ruitong Huang

Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. The certified radius in this context is a crucial indicator of the robustness of models. However…

Machine Learning · Computer Science 2024-03-19 Blaise Delattre , Alexandre Araujo , Quentin Barthélemy , Alexandre Allauzen

With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…

Machine Learning · Computer Science 2022-05-09 Pratik Vaishnavi , Kevin Eykholt , Amir Rahmati

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially…

Machine Learning · Computer Science 2026-03-16 Chenlong Yin , Runpeng Geng , Yanting Wang , Jinyuan Jia