Image de couverture de livre

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yu, Jiang, Han, Wei, Zhihua
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
par: Liu, Fan, et autres
Publié: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
par: Wang, Yihan, et autres
Publié: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
par: Zhang, Zhexin, et autres
Publié: (2023)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
par: Zhou, Andy, et autres
Publié: (2024)

Defending Against Social Engineering Attacks in the Age of LLMs
par: Ai, Lin, et autres
Publié: (2024)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
par: Zhao, Yinzhi, et autres
Publié: (2026)

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
par: Ji, Jiabao, et autres
Publié: (2024)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
par: Zhang, Zhexin, et autres
Publié: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
par: Xu, Zhangchen, et autres
Publié: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
par: Chu, Junjie, et autres
Publié: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
par: Wang, Zijun, et autres
Publié: (2024)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
par: Zhao, Jiawei, et autres
Publié: (2024)

Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?
par: Atil, Berk, et autres
Publié: (2025)

Intention Analysis Makes LLMs A Good Jailbreak Defender
par: Zhang, Yuqi, et autres
Publié: (2024)

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
par: Gao, Lang, et autres
Publié: (2024)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
par: Chen, Bocheng, et autres
Publié: (2024)

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
par: Feng, Yingchaojie, et autres
Publié: (2024)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
par: Hu, Xiaomeng, et autres
Publié: (2025)

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
par: Pu, Rui, et autres
Publié: (2024)

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
par: Jiang, Weisen, et autres
Publié: (2025)

Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
par: Wei, Zhipeng, et autres
Publié: (2024)

Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
par: Meng, Wenlong, et autres
Publié: (2025)

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
par: Li, Xiaoxia, et autres
Publié: (2024)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
par: Qian, Cheng, et autres
Publié: (2024)

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
par: Lv, Lijia, et autres
Publié: (2024)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
par: An, Li, et autres
Publié: (2025)

Defending Against Disinformation Attacks in Open-Domain Question Answering
par: Weller, Orion, et autres
Publié: (2022)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
par: Hines, Keegan, et autres
Publié: (2024)

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
par: Lin, Yuping, et autres
Publié: (2024)

SPML: A DSL for Defending Language Models Against Prompt Attacks
par: Sharma, Reshabh K, et autres
Publié: (2024)

Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
par: Lin, Liang, et autres
Publié: (2025)

Merging Improves Self-Critique Against Jailbreak Attacks
par: Gallego, Victor
Publié: (2024)

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
par: Cao, Bochuan, et autres
Publié: (2023)

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
par: Guo, Xingang, et autres
Publié: (2024)

TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
par: Xu, Zhi, et autres
Publié: (2026)

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
par: Zhu, Junda, et autres
Publié: (2025)

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
par: Wei, Zhihua, et autres
Publié: (2026)

CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
par: Mercier, Alexandre Le, et autres
Publié: (2026)

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
par: Noughabi, Havva Alizadeh, et autres
Publié: (2025)