Imagen de Portada

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Yuping, He, Pengfei, Xu, Han, Xing, Yue, Yamada, Makoto, Liu, Hui, Tang, Jiliang
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
por: Zeng, Shenglai, et al.
Publicado: (2024)

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
por: Zeng, Shenglai, et al.
Publicado: (2025)

Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
por: Lin, Liang, et al.
Publicado: (2025)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
por: Cui, Yingqian, et al.
Publicado: (2024)

Retrieval Heads are Dynamic
por: Lin, Yuping, et al.
Publicado: (2026)

Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study
por: He, Pengfei, et al.
Publicado: (2024)

TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
por: Xu, Zhi, et al.
Publicado: (2026)

Data Poisoning for In-context Learning
por: He, Pengfei, et al.
Publicado: (2024)

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

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

Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
por: Zhou, Yao, et al.
Publicado: (2026)

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

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
por: Hu, Xiaomeng, et al.
Publicado: (2025)

A Survey to Recent Progress Towards Understanding In-Context Learning
por: Mao, Haitao, et al.
Publicado: (2024)

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
por: Lee, Sunbowen, et al.
Publicado: (2025)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
por: Kadali, Sri Durga Sai Sowmya, et al.
Publicado: (2026)

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification
por: Li, Yu, et al.
Publicado: (2025)

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

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
por: Tang, Yihong, et al.
Publicado: (2024)

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
por: Luo, Xuan, et al.
Publicado: (2025)

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

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
por: Noughabi, Havva Alizadeh, et al.
Publicado: (2025)

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
por: Han, Haoyu, et al.
Publicado: (2025)

Automate Knowledge Concept Tagging on Math Questions with LLMs
por: Li, Hang, et al.
Publicado: (2024)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
por: Wang, Zijun, et al.
Publicado: (2024)

Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
por: Meng, Wenlong, et al.
Publicado: (2025)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
por: Liu, Xuannan, et al.
Publicado: (2024)

Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
por: Chen, Kexin, et al.
Publicado: (2024)

Enhancing Jailbreak Attacks with Diversity Guidance
por: Zhang, Xu, et al.
Publicado: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
por: Wang, Yihan, et al.
Publicado: (2024)

On Verbalized Confidence Scores for LLMs
por: Yang, Daniel, et al.
Publicado: (2024)

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
por: Guo, Xingang, et al.
Publicado: (2024)

Exploring Memorization in Fine-tuned Language Models
por: Zeng, Shenglai, et al.
Publicado: (2023)

SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis
por: Wong, Aidan, et al.
Publicado: (2024)

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
por: Poppi, Samuele, et al.
Publicado: (2024)

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
por: Cui, Yingqian, et al.
Publicado: (2025)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
por: Xing, Wenpeng, et al.
Publicado: (2025)

Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education
por: Yi, Xin, et al.
Publicado: (2025)

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

ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings
por: Wang, Hao, et al.
Publicado: (2024)