English
Related papers

Related papers: JPU: Bridging Jailbreak Defense and Unlearning via…

200 papers

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning…

Artificial Intelligence · Computer Science 2026-05-26 Seokil Ham , Jaehyuk Jang , Wonjun Lee , Changick Kim

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to…

Machine Learning · Computer Science 2026-02-03 Kaiyuan Cui , Yige Li , Yutao Wu , Xingjun Ma , Sarah Erfani , Christopher Leckie , Hanxun Huang

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Cryptography and Security · Computer Science 2025-11-19 Hajun Kim , Hyunsik Na , Daeseon Choi

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Computation and Language · Computer Science 2026-04-21 San Kim , Gary Geunbae Lee

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Artificial Intelligence · Computer Science 2026-03-13 Raj Sanjay Shah , Jing Huang , Keerthiram Murugesan , Nathalie Baracaldo , Diyi Yang

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Cryptography and Security · Computer Science 2026-05-12 Yu Chen , Yuanhao Liu , Qi Cao

The robustness of large language models (LLMs) against adversarial manipulations, such as jailbreak attacks, remains a significant challenge. In this work, we propose an approach that enhances the self-critique capability of the LLM and…

Computation and Language · Computer Science 2024-07-16 Victor Gallego

Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…

Machine Learning · Computer Science 2026-02-06 Licheng Pan , Yunsheng Lu , Jiexi Liu , Jialing Tao , Haozhe Feng , Hui Xue , Zhixuan Chu , Kui Ren

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

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

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

Cryptography and Security · Computer Science 2025-06-10 Yingchaojie Feng , Zhizhang Chen , Zhining Kang , Sijia Wang , Haoyu Tian , Wei Zhang , Minfeng Zhu , Wei Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Cryptography and Security · Computer Science 2026-03-04 Kalyan Nakka , Nitesh Saxena

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…

Cryptography and Security · Computer Science 2025-08-05 Man Hu , Yahui Ding , Yatao Yang , Liangyu Chen , Yanhao Jia , Shuai Zhao

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an…

Machine Learning · Computer Science 2024-02-07 Zhenxing Niu , Haodong Ren , Xinbo Gao , Gang Hua , Rong Jin