SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Security & robustness Adversarial Robustness in Machine Learning Digital and Cyber Forensics Advanced Malware Detection Techniques

Paper

The full text of this publication is not hosted on 44B due to licensing.

Read it at OpenAlex

Similar papers

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware DecodingZhangchen Xu, Fengqing Jiang, Luyao Niu et al.2024 · Annual Meeting of the Association for Computational Linguistics · 258 citations In Library

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness ProbingYinzhi Zhao, Ming Wang, Shi Feng et al.2026 · arXiv.org · 3 citations In Library

Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability DistributionsQuan Liu, Zhenhong Zhou, Longzhu He et al.2024 · Conference on Empirical Methods in Natural Language Processing · 13 citations In Library

AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language ModelsShilong Pan, Zhiliang Tian, Zhen Huang et al.2025 · Annual Meeting of the Association for Computational Linguistics · 3 citations In Library

DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software SystemsRui Yang, Michael Fu, C. Tantithamthavorn et al.2025 · arXiv.org · 0 citations In Library

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak DefenseChengqun Liu, Xiaolei Liu, Xingyu Li et al.2026 · Annual Meeting of the Association for Computational Linguistics · 1 citation In Library

Root Defence Strategies: Ensuring Safety of LLM at the Decoding LevelXinyi Zeng, Yuying Shang, Yutao Zhu et al.2024 · arXiv.org · 14 citations In Library

Defending Large Language Models against Jailbreak Attacks via Semantic SmoothingJiabao Ji, Bairu Hou, Alexander Robey et al.2025 In Library

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path RectificationXi Wang, Songlei Jian, Shasha Li et al.2026 In Library

RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMsT. Nguyen, John Le, T. Vu et al.2025 · arXiv.org · 0 citations In Library

Source of record

OpenAlex

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal