English
Related papers

Related papers: Rotated Robustness: A Training-Free Defense agains…

200 papers

Large Language Model (LLM) unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight its limited…

Computation and Language · Computer Science 2025-06-10 Xiaotian Ye , Mengqi Zhang , Shu Wu

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which…

Machine Learning · Computer Science 2020-06-17 Yiming Li , Baoyuan Wu , Yan Feng , Yanbo Fan , Yong Jiang , Zhifeng Li , Shutao Xia

Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model…

Cryptography and Security · Computer Science 2025-05-26 Linbao Li , Yannan Liu , Daojing He , Yu Li

Studies that broaden drone applications into complex tasks require a stable control framework. Recently, deep reinforcement learning (RL) algorithms have been exploited in many studies for robot control to accomplish complex tasks.…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

Cryptography and Security · Computer Science 2026-02-10 Jona te Lintelo , Lichao Wu , Stjepan Picek

The LLM unlearning technique has recently been introduced to comply with data regulations and address the safety and ethical concerns of LLMs by removing the undesired data-model influence. However, state-of-the-art unlearning methods face…

Machine Learning · Computer Science 2025-05-28 Chongyu Fan , Jinghan Jia , Yihua Zhang , Anil Ramakrishna , Mingyi Hong , Sijia Liu

Large Reasoning Models (LRMs) have recently demonstrated impressive performances across diverse domains. However, how the safety of Large Language Models (LLMs) benefits from enhanced reasoning capabilities against jailbreak queries remains…

Computation and Language · Computer Science 2025-09-23 Junda Zhu , Lingyong Yan , Shuaiqiang Wang , Dawei Yin , Lei Sha

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…

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Machine Learning · Computer Science 2024-02-28 Heegyu Kim , Sehyun Yuk , Hyunsouk Cho

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…

Machine Learning · Computer Science 2026-05-22 Rosie Zhao , Anshul Shah , Xiaoyu Zhu , Xinke Deng , Zhongyu Jiang , Yang Yang , Joerg Liebelt , Arnab Mondal

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Cryptography and Security · Computer Science 2026-04-06 John T. Halloran

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

Artificial Intelligence · Computer Science 2025-10-21 Zhehao Zhang , Weijie Xu , Shixian Cui , Chandan K. Reddy

As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studies assume that attackers rely on supervised fine-tuning (SFT) for such misuse, we systematically…

Machine Learning · Computer Science 2026-05-12 Weitao Feng , Lixu Wang , Peizhuo Lv , Tianyi Wei , Jie Zhang , Chongyang Gao , Sinong Zhan , Wei Dong

RL post-training for LLMs has been widely scaled to enhance reasoning and tool-using capabilities. However, RL post-training interleaves training and inference workloads, exposing the system to faults from both sides. Existing fault…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-30 Zhenqian Chen , Baoquan Zhong , Xiang Li , Qing Dai , Xinkui Zhao , Miao Ye , Ren Cheng , Lufei Zhang , Jianwei Yin

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

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…

Machine Learning · Computer Science 2024-10-28 Boyi Wei , Kaixuan Huang , Yangsibo Huang , Tinghao Xie , Xiangyu Qi , Mengzhou Xia , Prateek Mittal , Mengdi Wang , Peter Henderson

Extreme activation outliers in Large Language Models (LLMs) critically degrade quantization performance, hindering efficient on-device deployment. While channel-wise operations and adaptive gradient scaling are recognized causes, practical…

Machine Learning · Computer Science 2025-06-25 Jungwoo Park , Taewhoo Lee , Chanwoong Yoon , Hyeon Hwang , Jaewoo Kang
‹ Prev 1 3 4 5 6 7 10 Next ›