English
Related papers

Related papers: Differentiated Directional Intervention A Framewor…

200 papers

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the…

Computation and Language · Computer Science 2025-02-26 Weixuan Wang , Jingyuan Yang , Wei Peng

Safety has become one of the main challenges of applying deep reinforcement learning to real world systems. Currently, the incorporation of external knowledge such as human oversight is the only means to prevent the agent from visiting the…

Artificial Intelligence · Computer Science 2021-11-17 Yunkun Xu , Zhenyu Liu , Guifang Duan , Jiangcheng Zhu , Xiaolong Bai , Jianrong Tan

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Machine Learning · Computer Science 2026-05-05 Sadia Asif , Mohammad Mohammadi Amiri

Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversational safety mechanisms. We introduce Incremental Completion Decomposition (ICD), a…

Computation and Language · Computer Science 2026-04-30 Samee Arif , Naihao Deng , Zhijing Jin , Rada Mihalcea

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety alignment of VLMs is often achieved with post-hoc safety…

Cryptography and Security · Computer Science 2025-02-18 Fenghua Weng , Jian Lou , Jun Feng , Minlie Huang , Wenjie Wang

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Cryptography and Security · Computer Science 2024-12-10 Bryan Li , Sounak Bagchi , Zizhan Wang

Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the…

Cryptography and Security · Computer Science 2026-03-16 Jinman Wu , Yi Xie , Shen Lin , Shiqian Zhao , Xiaofeng Chen

Software vulnerability detection is generally supported by automated static analysis tools, which have recently been reinforced by deep learning (DL) models. However, despite the superior performance of DL-based approaches over rule-based…

Software Engineering · Computer Science 2024-05-03 Yanjing Yang , Xin Zhou , Runfeng Mao , Jinwei Xu , Lanxin Yang , Yu Zhangm , Haifeng Shen , He Zhang

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Jungwoo Park , Jaewoo Kang

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary…

Cryptography and Security · Computer Science 2026-04-29 Jonathan Steinberg , Oren Gal

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our…

Artificial Intelligence · Computer Science 2025-12-02 Haoxuan Ji , Zheng Lin , Zhenxing Niu , Xinbo Gao , Gang Hua

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Machine Learning · Computer Science 2024-06-04 Chujie Zheng , Fan Yin , Hao Zhou , Fandong Meng , Jie Zhou , Kai-Wei Chang , Minlie Huang , Nanyun Peng

LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These…

Cryptography and Security · Computer Science 2026-03-04 Yule Wen , Yanzhe Zhang , Jianxun Lian , Xiaoyuan Yi , Xing Xie , Diyi Yang

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Xiaohan Zou , Jian Kang , George Kesidis , Lu Lin

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

Machine Learning · Computer Science 2025-10-22 Jiawei Zhang , Andrew Estornell , David D. Baek , Bo Li , Xiaojun Xu

In this paper, we address the problems faced by a group of agents that possess situational awareness, but lack a security mechanism, by the introduction of a adaptive risk management system. The Belief-Desire-Intention (BDI) architecture…

Multiagent Systems · Computer Science 2013-08-20 Manu S Hegde , Sanjay Singh

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Cryptography and Security · Computer Science 2025-02-10 Guobin Shen , Dongcheng Zhao , Yiting Dong , Xiang He , Yi Zeng

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

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