Buchumschlag

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hu, Xiaomeng, Chen, Pin-Yu, Ho, Tsung-Yi
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

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

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

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

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
von: Hu, Xulin, et al.
Veröffentlicht: (2026)

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

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

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

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

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

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

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

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

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
von: Zou, Qingsong, et al.
Veröffentlicht: (2025)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
von: Jiang, Tanqiu, et al.
Veröffentlicht: (2024)

Is the System Message Really Important to Jailbreaks in Large Language Models?
von: Zou, Xiaotian, et al.
Veröffentlicht: (2024)

Imperceptible Jailbreaking against Large Language Models
von: Gao, Kuofeng, et al.
Veröffentlicht: (2025)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
von: Zhao, Shiji, et al.
Veröffentlicht: (2025)

A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models
von: Linder, Noa, et al.
Veröffentlicht: (2026)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
von: Wang, Libo
Veröffentlicht: (2024)

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
von: Ran, Delong, et al.
Veröffentlicht: (2024)

STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
von: Wang, Xunguang, et al.
Veröffentlicht: (2025)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
von: Li, Jie, et al.
Veröffentlicht: (2024)

Jailbreaking Large Language Models Through Content Concretization
von: Wahréus, Johan, et al.
Veröffentlicht: (2025)

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
von: Huang, Yao, et al.
Veröffentlicht: (2025)

JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
von: Luo, Weidi, et al.
Veröffentlicht: (2024)

ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
von: Cheng, Siyang, et al.
Veröffentlicht: (2025)

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

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

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
von: Li, Xiao, et al.
Veröffentlicht: (2024)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
von: Xu, Zihao, et al.
Veröffentlicht: (2024)

Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
von: Huang, Xijie, et al.
Veröffentlicht: (2024)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
von: Hua, Peichun, et al.
Veröffentlicht: (2025)

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

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
von: Zhao, Wei, et al.
Veröffentlicht: (2024)

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
von: Lv, Huijie, et al.
Veröffentlicht: (2024)

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

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

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

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
von: Chae, Kyubyung, et al.
Veröffentlicht: (2025)