Imagen de Portada

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Feng, Mingqian, Liu, Xiaodong, Yang, Weiwei, Song, Jialin, Zhu, Xuekai, Xu, Chenliang, Gao, Jianfeng
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
por: Song, Jialin, et al.
Publicado: (2026)

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
por: Zhang, Zeliang, et al.
Publicado: (2024)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
por: Zhang, Zeliang, et al.
Publicado: (2024)

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
por: Sun, Chung-En, et al.
Publicado: (2024)

Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
por: Feng, Mingqian, et al.
Publicado: (2026)

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

Many-Turn Jailbreaking
por: Yang, Xianjun, et al.
Publicado: (2025)

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
por: Sun, Xiongtao, et al.
Publicado: (2024)

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
por: Ma, Zhiqing, et al.
Publicado: (2026)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
por: Ying, Zonghao, et al.
Publicado: (2025)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
por: Zhang, Zeliang, et al.
Publicado: (2026)

DMON: A Simple yet Effective Approach for Argument Structure Learning
por: Sun, Wei, et al.
Publicado: (2024)

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
por: Cao, Hongye, et al.
Publicado: (2025)

SEP-Attack: A Simple and Effective Paradigm for Transfer-Based Textual Adversarial Attack
por: Liu, Han, et al.
Publicado: (2026)

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
por: Song, Dingjie, et al.
Publicado: (2024)

Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning
por: Wang, Yulong, et al.
Publicado: (2024)

Let the Bees Find the Weak Spots: A Path Planning Perspective on Multi-Turn Jailbreak Attacks against LLMs
por: Liu, Yize, et al.
Publicado: (2025)

Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
por: Gisserot-Boukhlef, Hippolyte, 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)

AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models
por: Shu, Dong, et al.
Publicado: (2024)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
por: Yu, Xiaodong, et al.
Publicado: (2023)

LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
por: Sun, Yizheng, et al.
Publicado: (2025)

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

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

Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
por: Zheng, Mingqian, et al.
Publicado: (2026)

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
por: Takemoto, Kazuhiro
Publicado: (2024)

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
por: Feng, Yingchaojie, et al.
Publicado: (2024)

Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks
por: Lee, Changho, et al.
Publicado: (2024)

PAST2HARM: A Simple Adaptive Past Tense Attack for Jailbreaking Multimodal AI
por: Mukhopadhyay, Snehasis
Publicado: (2026)

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

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

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

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
por: Li, Nathaniel, et al.
Publicado: (2024)

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
por: Mu, Honglin, et al.
Publicado: (2024)

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack
por: Zhu, Hai, et al.
Publicado: (2023)

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

SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
por: Dou, Yao, et al.
Publicado: (2025)

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
por: Miao, Ziqi, et al.
Publicado: (2025)

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

SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
por: Huang, Yongfeng, et al.
Publicado: (2026)