English
Related papers

Related papers: Mitigating Adaptive Attacks against Reasoning Mode…

200 papers

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Computation and Language · Computer Science 2025-02-24 Tianlong Li , Zhenghua Wang , Wenhao Liu , Muling Wu , Shihan Dou , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

Cryptography and Security · Computer Science 2025-04-24 Kuo-Han Hung , Ching-Yun Ko , Ambrish Rawat , I-Hsin Chung , Winston H. Hsu , Pin-Yu Chen

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on…

Machine Learning · Computer Science 2026-03-17 Vanshaj Khattar , Md Rafi ur Rashid , Moumita Choudhury , Jing Liu , Toshiaki Koike-Akino , Ming Jin , Ye Wang

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT introduces new safety challenges that extend beyond…

Artificial Intelligence · Computer Science 2025-09-30 Zihao Zhu , Xinyu Wu , Gehan Hu , Siwei Lyu , Ke Xu , Baoyuan Wu

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Fan Yang , Mingxuan Xia , Sangzhou Xia , Chicheng Ma , Hui Hui

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Machine Learning · Computer Science 2025-11-21 Zhe Wang , Yanjun Qi

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

Machine Learning · Computer Science 2024-11-15 Yifan Zeng , Yiran Wu , Xiao Zhang , Huazheng Wang , Qingyun Wu

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Cryptography and Security · Computer Science 2025-02-19 Xiaoqun Liu , Jiacheng Liang , Luoxi Tang , Muchao Ye , Weicheng Ma , Zhaohan Xi

Reasoning models have demonstrated remarkable capabilities in complex reasoning tasks. However, ensuring their safety against adversarial jailbreak prompts remains a critical challenge. Due to the covert and deceptive nature of such…

Computation and Language · Computer Science 2026-01-06 Yuhang Wang , Yanxu Zhu , Dongyuan Lu , Jitao Sang

Prompt injection poses a serious threat to the reliability and safety of LLM agents. Recent defenses against prompt injection, such as Instruction Hierarchy and SecAlign, have shown notable robustness against static attacks. However, to…

Cryptography and Security · Computer Science 2025-10-07 Yuxin Wen , Arman Zharmagambetov , Ivan Evtimov , Narine Kokhlikyan , Tom Goldstein , Kamalika Chaudhuri , Chuan Guo

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

Computation and Language · Computer Science 2026-02-10 Thilo Hagendorff , Erik Derner , Nuria Oliver

Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks. Although various advanced methods have been…

Machine Learning · Computer Science 2025-06-02 Haoyu Wang , Zeyu Qin , Li Shen , Xueqian Wang , Dacheng Tao , Minhao Cheng

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…

Cryptography and Security · Computer Science 2025-04-24 Senmao Qi , Yifei Zou , Peng Li , Ziyi Lin , Xiuzhen Cheng , Dongxiao Yu

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustness of LLMs to…

Computation and Language · Computer Science 2024-11-11 Esther Gan , Yiran Zhao , Liying Cheng , Yancan Mao , Anirudh Goyal , Kenji Kawaguchi , Min-Yen Kan , Michael Shieh

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…

Cryptography and Security · Computer Science 2025-10-27 Yukun Jiang , Mingjie Li , Michael Backes , Yang Zhang

Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malicious inputs is paramount for ensuring model safety.…

Cryptography and Security · Computer Science 2026-01-13 Jun Leng , Yu Liu , Litian Zhang , Ruihan Hu , Zhuting Fang , Xi Zhang
‹ Prev 1 8 9 10 Next ›