Cover Image

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Zheng, Niu, Zhenxing, Ji, Haoxuan, Huang, Yuzhe, Gao, Haichang
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Re-Triggering Safeguards within LLMs for Jailbreak Detection
by: Lin, Zheng, et al.
Published: (2026)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
by: Lin, Zheng, et al.
Published: (2026)

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
by: Ji, Haoxuan, et al.
Published: (2024)

Towards Aligned Data Removal via Twin Machine Unlearning
by: Ji, Haoxuan, et al.
Published: (2024)

Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
by: Wang, Yuhang, et al.
Published: (2026)

Robust MLLM Unlearning via Visual Knowledge Distillation
by: Wang, Yuhang, et al.
Published: (2025)

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
by: Wang, Yuhang, et al.
Published: (2026)

ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
by: Wang, Yuhang, et al.
Published: (2026)

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
by: Wu, Zihui, et al.
Published: (2024)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
by: Chen, Jianhao, et al.
Published: (2025)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

A Systematic Security Evaluation of OpenClaw and Its Variants
by: Wang, Yuhang, et al.
Published: (2026)

Imperceptible Jailbreaking against Large Language Models
by: Gao, Kuofeng, et al.
Published: (2025)

New Wide-Net-Casting Jailbreak Attacks Risk Large Models
by: Xiang, Qiuchi, et al.
Published: (2026)

BrainBench: Exposing the Commonsense Reasoning Gap in Large Language Models
by: Tang, Yuzhe
Published: (2026)

GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
by: Wu, Zihui, et al.
Published: (2024)

Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning
by: Yang, Pei, et al.
Published: (2025)

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
by: Zhao, Qinjian, et al.
Published: (2025)

Cross Modification Attention Based Deliberation Model for Image Captioning
by: Lian, Zheng, et al.
Published: (2021)

ShallowJail: Steering Jailbreaks against Large Language Models
by: Liu, Shang, et al.
Published: (2026)

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
by: Zhou, Weikang, et al.
Published: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
by: Zhao, Chongwen, et al.
Published: (2024)

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
by: Jiang, Fengqing, et al.
Published: (2024)

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
by: Yu, Jiahao, et al.
Published: (2023)

ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models
by: Chen, Bin, et al.
Published: (2025)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement Learning
by: Fanconi, Claudio, et al.
Published: (2025)

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
by: Wang, Yifan, et al.
Published: (2026)

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning
by: Bhambri, Siddhant, et al.
Published: (2024)

SoK: Robustness in Large Language Models against Jailbreak Attacks
by: Xu, Feiyue, et al.
Published: (2026)

Large Reasoning Models Are Autonomous Jailbreak Agents
by: Hagendorff, Thilo, et al.
Published: (2025)

Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models
by: Zhou, Ziqi, et al.
Published: (2024)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
by: Jin, Renren, et al.
Published: (2025)

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
by: Guo, Weiyang, et al.
Published: (2025)

Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models
by: Yang, Shidong, et al.
Published: (2026)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
by: Mao, Yingzhi, et al.
Published: (2025)

A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning
by: Wachi, Akifumi, et al.
Published: (2026)

Round Trip Translation Defence against Large Language Model Jailbreaking Attacks
by: Yung, Canaan, et al.
Published: (2024)

OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
by: Liang, Haijian, et al.
Published: (2026)

MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
by: Xu, Zekun, et al.
Published: (2025)