English
Related papers

Related papers: A Granular Study of Safety Pretraining under Model…

200 papers

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

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

Computation and Language · Computer Science 2025-02-18 Yanrui Du , Sendong Zhao , Jiawei Cao , Ming Ma , Danyang Zhao , Shuren Qi , Fenglei Fan , Ting Liu , Bing Qin

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an…

Cryptography and Security · Computer Science 2025-11-25 Peng Zhang , Peijie Sun

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly…

Cryptography and Security · Computer Science 2025-08-28 Chao Huang , Zefeng Zhang , Juewei Yue , Quangang Li , Chuang Zhang , Tingwen Liu

Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a…

Artificial Intelligence · Computer Science 2026-05-19 Jiahe Guo , Xiangran Guo , Jiaxuan Chen , Weixiang Zhao , Yanyan Zhao , Yutai Hou , Qianchao Wang , Dandan Tu , Bing Qin

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Cryptography and Security · Computer Science 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…

Computation and Language · Computer Science 2025-12-19 Shuzhou Yuan , Ercong Nie , Yinuo Sun , Chenxuan Zhao , William LaCroix , Michael Färber

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Computation and Language · Computer Science 2025-10-15 Trishna Chakraborty , Erfan Shayegani , Zikui Cai , Nael Abu-Ghazaleh , M. Salman Asif , Yue Dong , Amit K. Roy-Chowdhury , Chengyu Song

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Computation and Language · Computer Science 2025-06-12 Bang An , Sicheng Zhu , Ruiyi Zhang , Michael-Andrei Panaitescu-Liess , Yuancheng Xu , Furong Huang

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but…

Artificial Intelligence · Computer Science 2026-05-26 Qitao Tan , Xiaoying Song , Arman Akbari , Arash Akbari , Yanzhi Wang , Xiaoming Zhai , Lingzi Hong , Zhen Xiang , Jin Lu , Geng Yuan

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Computation and Language · Computer Science 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Cryptography and Security · Computer Science 2026-05-26 Lixing Lin , Juli You , Yue Li , Luyun Lin , Yiqing Wang , Zhen Zhang , Moxuan Zheng

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages…

Artificial Intelligence · Computer Science 2025-06-12 Jiachen Ma , Zhanhui Zhou , Chao Yang , Chaochao Lu

Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the impact of this framing bias on LLM-based evaluation, where…

Computation and Language · Computer Science 2026-01-21 Yerin Hwang , Dongryeol Lee , Taegwan Kang , Minwoo Lee , Kyomin Jung

The rapid growth of large language models has spurred significant interest in model compression as a means to enhance their accessibility and practicality. While extensive research has explored model compression through the lens of safety,…

Computation and Language · Computer Science 2025-04-08 Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

Machine Learning · Computer Science 2026-02-09 Navita Goyal , Hal Daumé

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safety training is that it algorithmically forbids the model…

Machine Learning · Computer Science 2024-02-09 Sophie Xhonneux , David Dobre , Jian Tang , Gauthier Gidel , Dhanya Sridhar

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Artificial Intelligence · Computer Science 2024-12-18 Zouying Cao , Yifei Yang , Hai Zhao
‹ Prev 1 4 5 6 7 8 10 Next ›