English
Related papers

Related papers: Adversarial Activation Patching: A Framework for D…

200 papers

As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks,…

Cryptography and Security · Computer Science 2025-02-13 Yang Ouyang , Hengrui Gu , Shuhang Lin , Wenyue Hua , Jie Peng , Bhavya Kailkhura , Meijun Gao , Tianlong Chen , Kaixiong Zhou

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Dehong Kong , Siyuan Liang , Xiaopeng Zhu , Yuansheng Zhong , Wenqi Ren

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Cryptography and Security · Computer Science 2026-05-13 Yassin H. Rassul , Tarik A. Rashid

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Cryptography and Security · Computer Science 2026-03-18 Ali Raza , Gurang Gupta , Nikolay Matyunin , Jibesh Patra

Adversarial patch attacks can fool the face recognition (FR) models via small patches. However, previous adversarial patch attacks often result in unnatural patterns that are easily noticeable. Generating transferable and stealthy…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Yanjie Li , Mingxing Duan , Xuelong Dai , Bin Xiao

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Cryptography and Security · Computer Science 2026-05-20 Ye Sun , Xin Wang , Jiaming Zhang , Yifeng Gao , Yixu Wang , Yifan Ding , Qixian Zhang , Henghui Ding , Xingjun Ma , Yu-Gang Jiang

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Computation and Language · Computer Science 2024-06-11 Duy C. Hoang , Quang H. Nguyen , Saurav Manchanda , MinLong Peng , Kok-Seng Wong , Khoa D. Doan

Adversarial examples have attracted widespread attention in security-critical applications because of their transferability across different models. Although many methods have been proposed to boost adversarial transferability, a gap still…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Xingxing Wei , Shiji Zhao

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…

Computation and Language · Computer Science 2024-12-11 Wangli Yang , Jie Yang , Yi Guo , Johan Barthelemy

While Large language model (LLM)-based programming assistants such as CoPilot and ChatGPT can help improve the productivity of professional software developers, they can also facilitate cheating in introductory computer programming courses.…

Computation and Language · Computer Science 2024-10-16 Saiful Islam Salim , Rubin Yuchan Yang , Alexander Cooper , Suryashree Ray , Saumya Debray , Sazzadur Rahaman

Adversarial examples have proven to be a concerning threat to deep learning models, particularly in the image domain. However, while many studies have examined adversarial examples in the real world, most of them relied on 2D photos of the…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Yael Mathov , Lior Rokach , Yuval Elovici

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…

Machine Learning · Computer Science 2023-12-07 Aleksandar Makelov , Georg Lange , Neel Nanda

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

Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations should not be readily trusted at face value. Recent studies…

Computation and Language · Computer Science 2024-11-04 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

The spread of fake news harms individuals and presents a critical social challenge that must be addressed. Although numerous algorithmic and insightful features have been developed to detect fake news, many of these features can be…

Computation and Language · Computer Science 2025-04-21 Sungwon Park , Sungwon Han , Xing Xie , Jae-Gil Lee , Meeyoung Cha

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Machine Learning · Computer Science 2026-02-24 Tim Beyer , Yan Scholten , Leo Schwinn , Stephan Günnemann

The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Lingxuan Wu , Xiao Yang , Yinpeng Dong , Liuwei Xie , Hang Su , Jun Zhu

Adversarial attacks on machine learning models have seen increasing interest in the past years. By making only subtle changes to the input of a convolutional neural network, the output of the network can be swayed to output a completely…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Simen Thys , Wiebe Van Ranst , Toon Goedemé

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

Computation and Language · Computer Science 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

The adoption of artificial intelligence (AI) across industries has led to the widespread use of complex black-box models and interpretation tools for decision making. This paper proposes an adversarial framework to uncover the vulnerability…

Machine Learning · Computer Science 2024-05-02 Xi Xin , Giles Hooker , Fei Huang