English
Related papers

Related papers: Circumventing Safety Alignment in Large Language M…

200 papers

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to…

Computation and Language · Computer Science 2025-06-04 Weikai Lu , Hao Peng , Huiping Zhuang , Cen Chen , Ziqian Zeng

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Machine Learning · Computer Science 2024-12-06 Jason Vega , Junsheng Huang , Gaokai Zhang , Hangoo Kang , Minjia Zhang , Gagandeep Singh

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

Robotics · Computer Science 2026-05-12 Kewei Chen , Yayu Long , Shuai Li , Mingsheng Shang

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…

Computation and Language · Computer Science 2024-10-14 Qin Liu , Chao Shang , Ling Liu , Nikolaos Pappas , Jie Ma , Neha Anna John , Srikanth Doss , Lluis Marquez , Miguel Ballesteros , Yassine Benajiba

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Artificial Intelligence · Computer Science 2025-04-22 Yuting Huang , Leilei Ding , Zhipeng Tang , Tianfu Wang , Xinrui Lin , Wuyang Zhang , Mingxiao Ma , Yanyong Zhang

Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where toxicity may combine semantic indirectness with surface obfuscation. We introduce Chinese Implicit…

Computation and Language · Computer Science 2026-05-22 Jingyi Kang , Junyu Lu , Bo Xu , Hongbo Wang , Linlin zong , Roy Ka-Wei Lee , Hongfei Lin

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Software Engineering · Computer Science 2025-01-09 Benjamin Steenhoek , Md Mahbubur Rahman , Monoshi Kumar Roy , Mirza Sanjida Alam , Hengbo Tong , Swarna Das , Earl T. Barr , Wei Le

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Computation and Language · Computer Science 2025-04-29 Alexandra Abbas , Nora Petrova , Helios Ael Lyons , Natalia Perez-Campanero

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

Large Language Models (LLMs) suffer severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and…

Machine Learning · Computer Science 2026-01-08 Shristi Das Biswas , Yue Zhang , Anwesan Pal , Radhika Bhargava , Kaushik Roy

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

Software Engineering · Computer Science 2025-12-23 Junyao Ye , Zhen Li , Xi Tang , Shouhuai Xu , Deqing Zou , Zhongsheng Yuan

Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat…

Computation and Language · Computer Science 2025-11-18 Md Rafi Ur Rashid , Vishnu Asutosh Dasu , Ye Wang , Gang Tan , Shagufta Mehnaz

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Cryptography and Security · Computer Science 2025-05-01 Ruochen Jiao , Shaoyuan Xie , Justin Yue , Takami Sato , Lixu Wang , Yixuan Wang , Qi Alfred Chen , Qi Zhu

Speech-LLM models have demonstrated great performance in multi-modal and multi-task speech understanding. A typical speech-LLM paradigm is integrating speech modality with a large language model (LLM). While the Whisper encoder was…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-11 Wei Liu , Jiahong Li , Yiwen Shao , Dong Yu

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

Cryptography and Security · Computer Science 2026-03-10 Neha Nagaraja , Hayretdin Bahsi

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

Cryptography and Security · Computer Science 2024-06-18 Stephen Burabari Tete