English
Related papers

Related papers: Self-Guard: Defending Large Reasoning Models via e…

200 papers

Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. In particular, while algorithms are designed to guide them to…

Machine Learning · Computer Science 2026-02-05 Zeming Wei , Qiaosheng Zhang , Xia Hu , Xingcheng Xu

The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic…

Computation and Language · Computer Science 2025-09-29 Wenbin Hu , Huihao Jing , Haochen Shi , Haoran Li , Yangqiu Song

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning…

Artificial Intelligence · Computer Science 2026-05-08 Xiaomin Li , Jianheng Hou , Zheyuan Deng , Zhiwei Zhang , Taoran Li , Binghang Lu , Bing Hu , Yunhan Zhao , Yuexing Hao

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Software Engineering · Computer Science 2026-04-03 Tyler Slater

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

Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, is widely considered among the most dangerous emergent…

Artificial Intelligence · Computer Science 2026-03-11 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Previous studies proposed that the reasoning capabilities of large language models (LLMs) can be improved through self-reflection, i.e., letting LLMs reflect on their own output to identify and correct mistakes in the initial responses.…

Computation and Language · Computer Science 2025-02-18 Fengyuan Liu , Nouar AlDahoul , Gregory Eady , Yasir Zaki , Talal Rahwan

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

Computation and Language · Computer Science 2025-10-16 Changyi Li , Jiayi Wang , Xudong Pan , Geng Hong , Min Yang

Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias)…

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Cryptography and Security · Computer Science 2026-04-15 Haotian Jin , Yang Li , Haihui Fan , Lin Shen , Xiangfang Li , Bo Li

Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge…

Cryptography and Security · Computer Science 2026-04-28 Qinfeng Li , Tianyue Luo , Xuhong Zhang , Yangfan Xie , Zhiqiang Shen , Lijun Zhang , Yier Jin , Hao Peng , Xinkui Zhao , Xianwei Zhu , Jianwei Yin

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Cryptography and Security · Computer Science 2025-10-10 Man Hu , Xinyi Wu , Zuofeng Suo , Jinbo Feng , Linghui Meng , Yanhao Jia , Anh Tuan Luu , Shuai Zhao

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

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

Cryptography and Security · Computer Science 2026-05-29 Zikai Zhang , Rui Hu , Olivera Kotevska , Jiahao Xu

The growing adoption of Large Language Models (LLMs) has influenced the development of Small Language Models (SLMs) for on-device deployment across smartphones and edge devices, offering enhanced privacy, reduced latency, server-free…

Cryptography and Security · Computer Science 2026-03-04 Kalyan Nakka , Jimmy Dani , Ausmit Mondal , Nitesh Saxena

Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Cryptography and Security · Computer Science 2026-04-01 Md Jueal Mia , Joaquin Molto , Yanzhao Wu , M. Hadi Amini

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
‹ Prev 1 4 5 6 7 8 10 Next ›