English
Related papers

Related papers: Benign Fine-Tuning Breaks Safety Alignment in Audi…

200 papers

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Computation and Language · Computer Science 2025-05-13 Brian R. Y. Huang , Maximilian Li , Leonard Tang

Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…

Sound · Computer Science 2026-01-22 Youngwon Choi , Jaeyoon Jung , Hyeonyu Kim , Huu-Kim Nguyen , Hwayeon Kim

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this work, we show that by…

Machine Learning · Computer Science 2026-03-03 Quoc Minh Nguyen , Trung Le , Jing Wu , Anh Tuan Bui , Mehrtash Harandi

Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility…

Sound · Computer Science 2026-04-13 Yunqiang Wang , Hengyuan Na , Di Wu , Miao Hu , Guocong Quan

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of…

Computation and Language · Computer Science 2026-02-02 Ye Yu , Haibo Jin , Yaoning Yu , Jun Zhuang , Haohan Wang

Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures,…

Machine Learning · Computer Science 2024-08-05 Jingtong Su , Julia Kempe , Karen Ullrich

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

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

Mental health disorders are increasingly prevalent worldwide, creating an urgent need for innovative tools to support early diagnosis and intervention. This study explores the potential of Large Language Models (LLMs) in multimodal mental…

Computation and Language · Computer Science 2025-08-14 Abdelrahman A. Ali , Aya E. Fouda , Radwa J. Hanafy , Mohammed E. Fouda

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…

Cryptography and Security · Computer Science 2026-04-24 Rui Yang Tan , Yujia Hu , Roy Ka-Wei Lee

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

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Computation and Language · Computer Science 2024-04-19 Jiabao Ji , Bairu Hou , Zhen Zhang , Guanhua Zhang , Wenqi Fan , Qing Li , Yang Zhang , Gaowen Liu , Sijia Liu , Shiyu Chang

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

Cryptography and Security · Computer Science 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to develop effective…

Computation and Language · Computer Science 2025-05-22 Lang Gao , Jiahui Geng , Xiangliang Zhang , Preslav Nakov , Xiuying Chen

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Computation and Language · Computer Science 2025-02-14 Riccardo Cantini , Giada Cosenza , Alessio Orsino , Domenico Talia

Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into…

Machine Learning · Computer Science 2025-06-10 Torsten Krauß , Hamid Dashtbani , Alexandra Dmitrienko

Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the attention sink mechanism to mitigate harmful fine-tuning. Specifically, we first measure a…

Artificial Intelligence · Computer Science 2026-02-12 Guozhi Liu , Weiwei Lin , Tiansheng Huang , Ruichao Mo , Qi Mu , Xiumin Wang , Li Shen

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert…

Cryptography and Security · Computer Science 2026-03-17 Zijian Ling , Pingyi Hu , Xiuyong Gao , Xiaojing Ma , Man Zhou , Jun Feng , Songfeng Lu , Dongmei Zhang , Bin Benjamin Zhu