English
Related papers

Related papers: CARE: Decoding Time Safety Alignment via Rollback …

200 papers

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

Artificial Intelligence · Computer Science 2025-10-27 Jingnan Zheng , Xiangtian Ji , Yijun Lu , Chenhang Cui , Weixiang Zhao , Gelei Deng , Zhenkai Liang , An Zhang , Tat-Seng Chua

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Computation and Language · Computer Science 2025-10-15 Divij Handa , Zehua Zhang , Amir Saeidi , Shrinidhi Kumbhar , Md Nayem Uddin , Aswin RRV , Chitta Baral

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and…

Cryptography and Security · Computer Science 2025-02-25 Hongfu Liu , Hengguan Huang , Xiangming Gu , Hao Wang , Ye Wang

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and…

Computation and Language · Computer Science 2025-12-16 Xiaoyun Zhang , Zhengyue Zhao , Wenxuan Shi , Kaidi Xu , Di Huang , Xing Hu

Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While existing research demonstrates that jailbreak attacks succeed, it does not explain…

Cryptography and Security · Computer Science 2026-02-11 Hayfa Dhabhi , Kashyap Thimmaraju

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g.,…

Computation and Language · Computer Science 2025-05-30 Feng Yao , Zilong Wang , Liyuan Liu , Junxia Cui , Li Zhong , Xiaohan Fu , Haohui Mai , Vish Krishnan , Jianfeng Gao , Jingbo Shang

Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, making it increasingly challenging for traditional threat…

Cryptography and Security · Computer Science 2025-10-31 Xihuan Lin , Jie Zhang , Gelei Deng , Tianzhe Liu , Tianwei Zhang , Qing Guo , Riqing Chen

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against…

Robotics · Computer Science 2025-09-03 Wenxiao Zhang , Xiangrui Kong , Conan Dewitt , Thomas Bräunl , Jin B. Hong

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

Machine Learning · Computer Science 2026-02-02 Zhewen Tan , Wenhan Yu , Jianfeng Si , Tongxin Liu , Kaiqi Guan , Huiyan Jin , Jiawen Tao , Xiaokun Yuan , Duohe Ma , Xiangzheng Zhang , Tong Yang , Lin Sun

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…

Machine Learning · Computer Science 2024-11-01 ShengYun Peng , Pin-Yu Chen , Matthew Hull , Duen Horng Chau

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained,…

Computation and Language · Computer Science 2026-01-21 Jianfeng Si , Lin Sun , Zhewen Tan , Xiangzheng Zhang

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

Computation and Language · Computer Science 2025-10-24 Jianhui Chen , Xiaozhi Wang , Zijun Yao , Yushi Bai , Lei Hou , Juanzi Li

In this paper, we propose a novel safety-critical control framework for a chain of integrators subject to both matched and mismatched perturbations. The core of our approach is a linear, time-varying state-feedback design that…

Systems and Control · Electrical Eng. & Systems 2025-10-01 Imtiaz Ur Rehman Moussa Labbadi , Amine Abadi , Lew Lew Yan Voon

Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce $\textbf{Latent Phase-Shift Rollback}$ (LPSR): at…

Machine Learning · Computer Science 2026-04-21 Manan Gupta , Dhruv Kumar

The increasing adoption of Cloud-based Large Language Models (CLLMs) has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often…

Cryptography and Security · Computer Science 2025-08-05 Dong Chen , Tong Yang , Feipeng Zhai , Pengpeng Ouyang , Qidong Liu , Yafei Li , Chong Fu , Mingliang Xu

We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…

Computation and Language · Computer Science 2025-04-08 Víctor Gallego

The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence…

Artificial Intelligence · Computer Science 2025-10-10 Joachim Diederich

Large Language Models are fundamental actors in the modern IT landscape dominated by AI solutions. However, security threats associated with them might prevent their reliable adoption in critical application scenarios such as government…

Cryptography and Security · Computer Science 2025-11-10 Marco Arazzi , Vignesh Kumar Kembu , Antonino Nocera , Vinod P

Aligning large language models (LLMs) with human preferences is essential for their applications. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that avoids fine-tuning model parameters. This approach…

Computation and Language · Computer Science 2025-08-05 Bolian Li , Yifan Wang , Anamika Lochab , Ananth Grama , Ruqi Zhang