Imagen de Portada

SafeDream: Safety World Model for Proactive Early Jailbreak Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan, Bo, Lin, Weikai, Zhu, Yada, Wang, Song
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
por: Yang, Xianglin, et al.
Publicado: (2025)

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
por: Liang, Siyuan, et al.
Publicado: (2025)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
por: Xu, Zhangchen, et al.
Publicado: (2024)

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
por: Song, Weiming, et al.
Publicado: (2026)

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
por: Nian, Yi, et al.
Publicado: (2025)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
por: Yang, Fan
Publicado: (2025)

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
por: Wang, Ziwei, et al.
Publicado: (2026)

Re-Triggering Safeguards within LLMs for Jailbreak Detection
por: Lin, Zheng, et al.
Publicado: (2026)

Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
por: Wu, Jinman, et al.
Publicado: (2026)

Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
por: Hong, Wenjing, et al.
Publicado: (2026)

PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
por: Gai, Keke, et al.
Publicado: (2025)

Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach
por: Huang, Bing, et al.
Publicado: (2024)

SDD: Self-Degraded Defense against Malicious Fine-tuning
por: Chen, Zixuan, et al.
Publicado: (2025)

Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation
por: Zhang, Wenhui, et al.
Publicado: (2025)

SoK: Evaluating Jailbreak Guardrails for Large Language Models
por: Wang, Xunguang, et al.
Publicado: (2025)

Proactively Detecting Threats: A Novel Approach Using LLMs
por: Chawla, Aniesh, et al.
Publicado: (2026)

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
por: Lin, Shuyi, et al.
Publicado: (2025)

SoK: Robustness in Large Language Models against Jailbreak Attacks
por: Xu, Feiyue, et al.
Publicado: (2026)

NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks
por: Sleem, Lama, et al.
Publicado: (2025)

DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
por: Wang, Yi, et al.
Publicado: (2025)

Untargeted Jailbreak Attack
por: Huang, Xinzhe, et al.
Publicado: (2025)

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
por: Liu, Zehao, et al.
Publicado: (2025)

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
por: Yan, Yu, et al.
Publicado: (2025)

SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
por: Fang, Xianya, et al.
Publicado: (2026)

Proactive Detection of Voice Cloning with Localized Watermarking
por: Roman, Robin San, et al.
Publicado: (2024)

Emoji-Based Jailbreaking of Large Language Models
por: Gopinadh, M P V S, et al.
Publicado: (2026)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
por: Wang, Zhaoqi, et al.
Publicado: (2025)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
por: Lin, Zheng, et al.
Publicado: (2026)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
por: Fang, Junfeng, et al.
Publicado: (2025)

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
por: Wu, Zihui, et al.
Publicado: (2024)

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
por: Li, Wenjie, et al.
Publicado: (2025)

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
por: Wang, Hao, et al.
Publicado: (2026)

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
por: Gong, Xueluan, et al.
Publicado: (2024)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
por: Zhou, Kaiwen, et al.
Publicado: (2025)

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
por: Zeng, Yi, et al.
Publicado: (2024)

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
por: Pramanik, Vishal, et al.
Publicado: (2026)

ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack
por: Lin, Xingwei, et al.
Publicado: (2026)

Gradient-based Jailbreak Images for Multimodal Fusion Models
por: Rando, Javier, et al.
Publicado: (2024)

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges
por: Li, Haoyang, et al.
Publicado: (2025)

EVA: Editing for Versatile Alignment against Jailbreaks
por: Wang, Yi, et al.
Publicado: (2026)