English
Related papers

Related papers: NeuRel-Attack: Neuron Relearning for Safety Disali…

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Cryptography and Security · Computer Science 2025-06-03 Jie Ren , Zhenwei Dai , Xianfeng Tang , Yue Xing , Shenglai Zeng , Hui Liu , Jingying Zeng , Qiankun Peng , Samarth Varshney , Suhang Wang , Qi He , Charu C. Aggarwal , Hui Liu

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Computation and Language · Computer Science 2024-06-25 Simone Tedeschi , Felix Friedrich , Patrick Schramowski , Kristian Kersting , Roberto Navigli , Huu Nguyen , Bo Li

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

Large language models (LLMs) are still struggling in aligning with human preference in complex tasks and scenarios. They are prone to overfit into the unexpected patterns or superficial styles in the training data. We conduct an empirical…

Computation and Language · Computer Science 2024-10-04 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Jingyuan Wang , Ji-Rong Wen

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Cryptography and Security · Computer Science 2024-04-29 Kongyang Chen , Zixin Wang , Bing Mi , Waixi Liu , Shaowei Wang , Xiaojun Ren , Jiaxing Shen

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence · Computer Science 2026-02-03 Abhishek Mishra , Mugilan Arulvanan , Reshma Ashok , Polina Petrova , Deepesh Suranjandass , Donnie Winkelmann

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Machine Learning · Computer Science 2025-06-25 Shuang Ao , Yi Dong , Jinwei Hu , Sarvapali Ramchurn

Currently, large models are prone to generating harmful content when faced with complex attack instructions, significantly reducing their defensive capabilities. To address this issue, this paper proposes a method based on constructing data…

Cryptography and Security · Computer Science 2025-01-03 Keke Zhai

Deep neural networks have achieved remarkable success across various applications; however, their vulnerability to backdoor attacks poses severe security risks -- especially in situations where only a limited set of clean samples is…

Cryptography and Security · Computer Science 2025-06-25 Nay Myat Min , Long H. Pham , Jun Sun

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Cryptography and Security · Computer Science 2025-11-13 Daniyal Ganiuly , Assel Smaiyl

Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A common mitigation strategy is to update the model more strongly…

Machine Learning · Computer Science 2025-12-23 ShengYun Peng , Pin-Yu Chen , Jianfeng Chi , Seongmin Lee , Duen Horng Chau

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

Computation and Language · Computer Science 2025-06-17 Philipp Spohn , Leander Girrbach , Jessica Bader , Zeynep Akata

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Cryptography and Security · Computer Science 2025-12-17 Fan Yang

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Computation and Language · Computer Science 2026-04-21 Zhexin Zhang , Xian Qi Loye , Victor Shea-Jay Huang , Junxiao Yang , Qi Zhu , Shiyao Cui , Fei Mi , Lifeng Shang , Yingkang Wang , Hongning Wang , Minlie Huang

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Computation and Language · Computer Science 2025-06-24 Yilei Jiang , Xinyan Gao , Tianshuo Peng , Yingshui Tan , Xiaoyong Zhu , Bo Zheng , Xiangyu Yue

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Cryptography and Security · Computer Science 2024-05-31 Weilin Lin , Li Liu , Shaokui Wei , Jianze Li , Hui Xiong

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

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…

Machine Learning · Computer Science 2020-10-29 Krishnan Srinivasan , Benjamin Eysenbach , Sehoon Ha , Jie Tan , Chelsea Finn