Imagen de Portada

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hu, Xiaomeng, Chen, Pin-Yu, Ho, Tsung-Yi
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
por: Hu, Xiaomeng, et al.
Publicado: (2024)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
por: Ni, Ziyi, et al.
Publicado: (2025)

How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation
por: Long, Zhuohang, et al.
Publicado: (2025)

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
por: Pu, Rui, et al.
Publicado: (2024)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
por: Xiong, Chen, et al.
Publicado: (2024)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
por: Xu, Zhao, et al.
Publicado: (2024)

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
por: Ouyang, Yang, et al.
Publicado: (2025)

Jailbreak Attacks and Defenses Against Large Language Models: A Survey
por: Yi, Sibo, et al.
Publicado: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
por: Liu, Fan, et al.
Publicado: (2024)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
por: Akbar-Tajari, Mohammad, et al.
Publicado: (2025)

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
por: Lv, Lijia, et al.
Publicado: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
por: Chen, Taiye, et al.
Publicado: (2025)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
por: Gohil, Vasudev
Publicado: (2025)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
por: Kirch, Nathalie, et al.
Publicado: (2024)

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
por: Hu, Xiaomeng, et al.
Publicado: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
por: Chu, Junjie, et al.
Publicado: (2024)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
por: Tu, Shangqing, et al.
Publicado: (2024)

Activation-Guided Local Editing for Jailbreaking Attacks
por: Wang, Jiecong, et al.
Publicado: (2025)

Distract Large Language Models for Automatic Jailbreak Attack
por: Xiao, Zeguan, et al.
Publicado: (2024)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
por: Xu, Naen, et al.
Publicado: (2026)

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
por: Yan, Dong, et al.
Publicado: (2026)

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
por: Yu, Yongcan, et al.
Publicado: (2025)

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
por: Xiong, Chen, et al.
Publicado: (2026)

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
por: Jiang, Weisen, et al.
Publicado: (2025)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
por: Yu, Miao, et al.
Publicado: (2024)

Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
por: Zhao, Yi, et al.
Publicado: (2025)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
por: Mehrotra, Anay, et al.
Publicado: (2023)

Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
por: Shang, Zhengchun, et al.
Publicado: (2025)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
por: Xu, Zihao, et al.
Publicado: (2024)

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
por: Yi, Sibo, et al.
Publicado: (2025)

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
por: Yang, Yan, et al.
Publicado: (2024)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
por: Mu, Junjie, et al.
Publicado: (2025)

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
por: Zhou, Guanghao, et al.
Publicado: (2025)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
por: Zhao, Jiawei, et al.
Publicado: (2024)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
por: Kabir, Md Rysul, et al.
Publicado: (2026)

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
por: Gibbs, Tom, et al.
Publicado: (2024)

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
por: Tong, Haibo, et al.
Publicado: (2025)

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
por: Li, Xirui, et al.
Publicado: (2024)

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks
por: Pandya, Nishit V., et al.
Publicado: (2025)

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
por: Liu, Xiaoqun, et al.
Publicado: (2024)