English
Related papers

Related papers: Stealthy and Persistent Unalignment on Large Langu…

200 papers

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…

Cryptography and Security · Computer Science 2024-03-21 Yanzhou Li , Tianlin Li , Kangjie Chen , Jian Zhang , Shangqing Liu , Wenhan Wang , Tianwei Zhang , Yang Liu

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Computation and Language · Computer Science 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Machine Learning · Computer Science 2026-03-03 Yuhui Wang , Rongyi Zhu , Ting Wang

Recent years have witnessed remarkable progress made in large language models (LLMs). Such advancements, while garnering significant attention, have concurrently elicited various concerns. The potential of these models is undeniably vast;…

Computation and Language · Computer Science 2023-09-27 Tianhao Shen , Renren Jin , Yufei Huang , Chuang Liu , Weilong Dong , Zishan Guo , Xinwei Wu , Yan Liu , Deyi Xiong

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Artificial Intelligence · Computer Science 2024-11-05 Lingkai Kong , Haorui Wang , Wenhao Mu , Yuanqi Du , Yuchen Zhuang , Yifei Zhou , Yue Song , Rongzhi Zhang , Kai Wang , Chao Zhang

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…

Computation and Language · Computer Science 2026-01-21 Xuhao Hu , Peng Wang , Xiaoya Lu , Dongrui Liu , Xuanjing Huang , Jing Shao

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during…

Machine Learning · Computer Science 2026-01-07 Jiawen Zhang , Lipeng He , Kejia Chen , Jian Lou , Jian Liu , Xiaohu Yang , Ruoxi Jia

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

Machine Learning · Computer Science 2025-01-22 Haonan Shi , Tu Ouyang , An Wang

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yangqiu Song , Bryan Hooi

Large Language Models (LLMs) have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misused to generate undesired content. In response, before…

Machine Learning · Computer Science 2023-10-04 Hangfan Zhang , Zhimeng Guo , Huaisheng Zhu , Bochuan Cao , Lu Lin , Jinyuan Jia , Jinghui Chen , Dinghao Wu

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

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Cryptography and Security · Computer Science 2025-02-18 Huaizhi Ge , Yiming Li , Qifan Wang , Yongfeng Zhang , Ruixiang Tang

Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical…

Computation and Language · Computer Science 2026-04-24 Aladin Djuhera , Swanand Ravindra Kadhe , Farhan Ahmed , Syed Zawad , Holger Boche

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

Cryptography and Security · Computer Science 2025-02-11 Michele Miranda , Elena Sofia Ruzzetti , Andrea Santilli , Fabio Massimo Zanzotto , Sébastien Bratières , Emanuele Rodolà

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang