English
Related papers

Related papers: AutoDAN-Reasoning: Enhancing Strategies Exploratio…

200 papers

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

Cryptography and Security · Computer Science 2025-11-21 Zhen Sun , Zongmin Zhang , Deqi Liang , Han Sun , Yule Liu , Yun Shen , Xiangshan Gao , Yilong Yang , Shuai Liu , Yutao Yue , Xinlei He

Recent research has focused on exploring the vulnerabilities of Large Language Models (LLMs), aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting…

Cryptography and Security · Computer Science 2025-10-07 Xinzhe Huang , Kedong Xiu , Tianhang Zheng , Churui Zeng , Wangze Ni , Zhan Qin , Kui Ren , Chun Chen

Optimization methods are widely employed in deep learning to identify and mitigate undesired model responses. While gradient-based techniques have proven effective for image models, their application to language models is hindered by the…

Machine Learning · Computer Science 2025-02-18 Zi Wang , Divyam Anshumaan , Ashish Hooda , Yudong Chen , Somesh Jha

This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…

Machine Learning · Computer Science 2025-10-10 Weisen Jiang , Sinno Jialin Pan

Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We instead optimize the strategy. We propose AutoRISE, a method…

Cryptography and Security · Computer Science 2026-04-28 Tanmay Gautam , Alireza Bahramali , Sandeep Atluri

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Aarush Noheria , Yuguang Yao

This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy. We first observe a positive…

Computation and Language · Computer Science 2024-10-14 Zijun Wang , Haoqin Tu , Jieru Mei , Bingchen Zhao , Yisen Wang , Cihang Xie

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate…

Computation and Language · Computer Science 2023-10-23 Yuchen Zhuang , Xiang Chen , Tong Yu , Saayan Mitra , Victor Bursztyn , Ryan A. Rossi , Somdeb Sarkhel , Chao Zhang

Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow,…

Computation and Language · Computer Science 2025-07-08 James Beetham , Souradip Chakraborty , Mengdi Wang , Furong Huang , Amrit Singh Bedi , Mubarak Shah

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Cryptography and Security · Computer Science 2025-10-10 Xiangfang Li , Yu Wang , Bo Li

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Yunhan Zhao , Xiang Zheng , Xingjun Ma

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Computation and Language · Computer Science 2024-02-26 Yanrui Du , Sendong Zhao , Ming Ma , Yuhan Chen , Bing Qin

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…

Artificial Intelligence · Computer Science 2026-04-21 Jingbo Sun , Wenyue Chong , Songjun Tu , Qichao Zhang , Yaocheng Zhang , Jiajun Chai , Xiaohan Wang , Wei Lin , Guojun Yin , Dongbin Zhao

As large language models (LLMs) become increasingly prevalent, ensuring their robustness against adversarial misuse is crucial. This paper introduces the GAP (Graph of Attacks with Pruning) framework, an advanced approach for generating…

Cryptography and Security · Computer Science 2025-11-14 Daniel Schwartz , Dmitriy Bespalov , Zhe Wang , Ninad Kulkarni , Yanjun Qi

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Cryptography and Security · Computer Science 2025-02-24 Pedram Zaree , Md Abdullah Al Mamun , Quazi Mishkatul Alam , Yue Dong , Ihsen Alouani , Nael Abu-Ghazaleh

Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Language Model (LLM) applications, especially chatbots.…

Cryptography and Security · Computer Science 2025-08-26 Junchen Ding , Jiahao Zhang , Yi Liu , Ziqi Ding , Gelei Deng , Yuekang Li

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical…

Artificial Intelligence · Computer Science 2015-11-23 Bradly C. Stadie , Sergey Levine , Pieter Abbeel

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Cryptography and Security · Computer Science 2026-05-13 Xinkai Zhang , Zhipeng Wei , Huanli Gong , Jing Ting Zheng , Yuchen Zhang , Yue Dong , N. Benjamin Erichson

Test-time scaling enhances large language model performance by allocating additional compute resources during inference. Best-of-N (BoN) sampling serves as a common sampling-based scaling technique, broadening the search space in parallel…

Computation and Language · Computer Science 2025-11-04 Yiming Wang , Pei Zhang , Siyuan Huang , Baosong Yang , Zhuosheng Zhang , Fei Huang , Rui Wang

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren
‹ Prev 1 4 5 6 7 8 10 Next ›