中文
相关论文

相关论文: AutoRAN: Automated Hijacking of Safety Reasoning i…

200 篇论文

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

计算与语言 · 计算机科学 2026-02-10 Thilo Hagendorff , Erik Derner , Nuria Oliver

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue…

人工智能 · 计算机科学 2026-04-22 Yeonjun In , Wonjoong Kim , Sangwu Park , Chanyoung Park

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

密码学与安全 · 计算机科学 2023-12-15 Sicheng Zhu , Ruiyi Zhang , Bang An , Gang Wu , Joe Barrow , Zichao Wang , Furong Huang , Ani Nenkova , Tong Sun

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

密码学与安全 · 计算机科学 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary:…

人工智能 · 计算机科学 2026-05-26 Jianli Zhao , Tingchen Fu , Rylan Schaeffer , Mrinank Sharma , Fazl Barez

Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…

密码学与安全 · 计算机科学 2025-06-04 Yang Yao , Xuan Tong , Ruofan Wang , Yixu Wang , Lujundong Li , Liang Liu , Yan Teng , Yingchun Wang

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

人工智能 · 计算机科学 2026-01-27 Xin Gao , Shaohan Yu , Zerui Chen , Yueming Lyu , Weichen Yu , Guanghao Li , Jiyao Liu , Jianxiong Gao , Jian Liang , Ziwei Liu , Chenyang Si

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce…

密码学与安全 · 计算机科学 2025-10-24 Jingyuan Ma , Rui Li , Zheng Li , Junfeng Liu , Heming Xia , Lei Sha , Zhifang Sui

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

人工智能 · 计算机科学 2026-02-03 Jingnan Zheng , Jingjun Xu , Yanzhen Luo , Chenhang Cui , Gelei Deng , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

密码学与安全 · 计算机科学 2025-10-24 Shuo Chen , Zhen Han , Haokun Chen , Bailan He , Shengyun Si , Jingpei Wu , Philip Torr , Volker Tresp , Jindong Gu

The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, these large models remain susceptible to jailbreak attacks,…

计算与语言 · 计算机科学 2024-03-22 Xiaogeng Liu , Nan Xu , Muhao Chen , Chaowei Xiao

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

密码学与安全 · 计算机科学 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

机器学习 · 计算机科学 2025-10-21 Mohan Zhang , Yihua Zhang , Jinghan Jia , Zhangyang Wang , Sijia Liu , Tianlong Chen

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

机器学习 · 计算机科学 2025-04-15 Junfeng Fang , Yukai Wang , Ruipeng Wang , Zijun Yao , Kun Wang , An Zhang , Xiang Wang , Tat-Seng Chua

Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To address this overlooked risk, we first propose a novel attack…

人工智能 · 计算机科学 2026-01-01 Jianhao Chen , Mayi Xu , Haoyang Chen , Xiaohu Li , Xiangyu Zhang , Jianjie Huang , Zheng Wang , Xiaochun Cao , Tieyun Qian

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

人工智能 · 计算机科学 2025-10-24 Wonje Jeung , Sangyeon Yoon , Minsuk Kahng , Albert No

Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes domains such as healthcare and education. While prior…

机器学习 · 计算机科学 2026-04-20 Zehao Wang , Lanjun Wang

Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current…

计算与语言 · 计算机科学 2026-05-07 Yuquan Wang , Mi Zhang , Yining Wang , Geng Hong , Mi Wen , Xiaoyu You , Min Yang

Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructions, raising significant safety concerns. In this paper, we…

人工智能 · 计算机科学 2025-08-04 Yeonjun In , Wonjoong Kim , Sangwu Park , Chanyoung Park

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their…

‹ 上一页 1 2 3 10 下一页 ›