English
Related papers

Related papers: Lightweight Lipschitz Margin Training for Certifie…

200 papers

Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to imperceptible perturbations, creating serious risks when…

Machine Learning · Computer Science 2024-11-04 Jonas Ngnawé , Sabyasachi Sahoo , Yann Pequignot , Frédéric Precioso , Christian Gagné

Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable to adversarial examples, posing a question regarding their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-13 Akshayvarun Subramanya , Hamed Pirsiavash

Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems. In line with approaches from robust…

Machine Learning · Computer Science 2021-12-21 Thomas T. C. K. Zhang , Stephen Tu , Nicholas M. Boffi , Jean-Jacques E. Slotine , Nikolai Matni

Recent studies show that deep neural networks (DNN) are vulnerable to adversarial examples, which aim to mislead DNNs by adding perturbations with small magnitude. To defend against such attacks, both empirical and theoretical defense…

Machine Learning · Computer Science 2022-04-22 Zhuolin Yang , Linyi Li , Xiaojun Xu , Bhavya Kailkhura , Tao Xie , Bo Li

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Cryptography and Security · Computer Science 2025-06-02 Xin Yi , Yue Li , Dongsheng Shi , Linlin Wang , Xiaoling Wang , Liang He

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

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

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

Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Sibo Wang , Jie Zhang , Zheng Yuan , Shiguang Shan

Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric…

Machine Learning · Computer Science 2024-08-20 Yun-Da Tsai , Ting-Yu Yen , Keng-Te Liao , Shou-De Lin

Recently, adversarial training has been incorporated in self-supervised contrastive pre-training to augment label efficiency with exciting adversarial robustness. However, the robustness came at a cost of expensive adversarial training. In…

Machine Learning · Computer Science 2022-11-01 Yijiang Pang , Boyang Liu , Jiayu Zhou

Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against $\ell_2$ norm bounded…

Machine Learning · Statistics 2020-02-19 Huijie Feng , Chunpeng Wu , Guoyang Chen , Weifeng Zhang , Yang Ning

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

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

Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this…

Computation and Language · Computer Science 2024-10-17 Hao-Yuan Chang , Kang L. Wang

Despite its popularity, deep neural networks are easily fooled. To alleviate this deficiency, researchers are actively developing new training strategies, which encourage models that are robust to small input perturbations. Several…

Machine Learning · Computer Science 2021-10-28 Jingyue Lu , M. Pawan Kumar

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks…

Cryptography and Security · Computer Science 2025-05-05 Jinsheng Pan , Xiaogeng Liu , Chaowei Xiao

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Xiaojun Jia , Yuefeng Chen , Xiaofeng Mao , Ranjie Duan , Jindong Gu , Rong Zhang , Hui Xue , Xiaochun Cao

We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a novel robust training…

Computation and Language · Computer Science 2022-07-28 Yichen Yang , Xiaosen Wang , Kun He

Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Xin Wang , Kai Chen , Jiaming Zhang , Jingjing Chen , Xingjun Ma