English
Related papers

Related papers: NeST: Neuron Selective Tuning for LLM Safety

200 papers

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security…

Cryptography and Security · Computer Science 2025-04-08 Shen Li , Liuyi Yao , Lan Zhang , Yaliang Li

Fine-tuning large language models (LLMs) is often limited by the memory available on commodity GPUs. Parameter-efficient fine-tuning (PEFT) methods such as QLoRA reduce the number of trainable parameters, yet still incur high memory usage…

Computation and Language · Computer Science 2025-12-17 Estelle Zheng , Nathan Cerisara , Sébastien Warichet , Emmanuel Helbert , Christophe Cerisara

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian

The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing (NLP) and related fields. However, fine-tuning these models for specific tasks remains computationally expensive and risks degrading…

Computation and Language · Computer Science 2024-12-17 Md Kowsher , Nusrat Jahan Prottasha , Prakash Bhat

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

Machine Learning · Computer Science 2025-07-29 Gabriel J. Perin , Runjin Chen , Xuxi Chen , Nina S. T. Hirata , Zhangyang Wang , Junyuan Hong

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Machine Learning · Computer Science 2026-02-10 Kaustubh Ponkshe , Shaan Shah , Raghav Singhal , Praneeth Vepakomma

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Computation and Language · Computer Science 2026-03-10 Guoli Wang , Haonan Shi , Tu Ouyang , An Wang

Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives…

Computation and Language · Computer Science 2023-12-08 Jaehyung Kim , Yuning Mao , Rui Hou , Hanchao Yu , Davis Liang , Pascale Fung , Qifan Wang , Fuli Feng , Lifu Huang , Madian Khabsa

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Machine Learning · Computer Science 2025-07-08 Jeremiah Giordani

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

Machine Learning · Computer Science 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

Artificial Intelligence · Computer Science 2025-10-24 Wonje Jeung , Sangyeon Yoon , Minsuk Kahng , Albert No

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Cryptography and Security · Computer Science 2025-09-05 Chuhan Zhang , Ye Zhang , Bowen Shi , Yuyou Gan , Tianyu Du , Shouling Ji , Dazhan Deng , Yingcai Wu

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

Computation and Language · Computer Science 2025-10-20 Aaron Zheng , Mansi Rana , Andreas Stolcke

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Computation and Language · Computer Science 2026-01-09 Sharanya Dasgupta , Arkaprabha Basu , Sujoy Nath , Swagatam Das

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

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…

Computers and Society · Computer Science 2026-02-03 Guanghao Zhou , Panjia Qiu , Cen Chen , Hongyu Li , Mingyuan Chu , Xin Zhang , Jun Zhou

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo