Cover Image

On the Role of Attention Heads in Large Language Model Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Zhenhong, Yu, Haiyang, Zhang, Xinghua, Xu, Rongwu, Huang, Fei, Wang, Kun, Liu, Yang, Fang, Junfeng, Li, Yongbin
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

Resource Consumption Red-Teaming for Large Vision-Language Models
by: Gao, Haoran, et al.
Published: (2025)

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

Resource Consumption Threats in Large Language Models
by: Zhang, Yuanhe, et al.
Published: (2026)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
by: Xu, Rongwu, et al.
Published: (2024)

$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models
by: Zhang, Yuanhe, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just A Few Attention Heads
by: Huang, Chao, et al.
Published: (2025)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
by: Yuan, Xiaohan, et al.
Published: (2024)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
by: Zhang, Junbo, et al.
Published: (2025)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
by: Zhang, Yuanhe, et al.
Published: (2025)

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
by: Wu, Jialin, et al.
Published: (2025)

Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training
by: Xu, Rongwu, et al.
Published: (2024)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
by: Gu, Tianle, et al.
Published: (2024)

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
by: Wu, Yihan, et al.
Published: (2023)

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
by: Zhou, Zhenhong, et al.
Published: (2026)

Representation Bending for Large Language Model Safety
by: Yousefpour, Ashkan, et al.
Published: (2025)

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
by: Li, Ting, et al.
Published: (2025)

Privacy-Preserving Instructions for Aligning Large Language Models
by: Yu, Da, et al.
Published: (2024)

Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators
by: Li, Xitao, et al.
Published: (2025)

FNF: Functional Network Fingerprint for Large Language Models
by: Liu, Yiheng, et al.
Published: (2026)

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

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
by: Zhou, Tong, et al.
Published: (2024)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
by: Shen, Guobin, et al.
Published: (2024)

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
by: Gu, Haoran, et al.
Published: (2025)

Proactive defense against LLM Jailbreak
by: Zhao, Weiliang, et al.
Published: (2025)

Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
by: Xu, Rongwu, et al.
Published: (2025)

CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
by: Zhang, Yu, et al.
Published: (2025)

AICrypto: Evaluating Cryptography Capabilities of Large Language Models
by: Wang, Yu, et al.
Published: (2025)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
by: Li, Yansong, et al.
Published: (2023)

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, et al.
Published: (2025)

Prompt Stealing Attacks Against Large Language Models
by: Sha, Zeyang, et al.
Published: (2024)

FIT to Forget: Robust Continual Unlearning for Large Language Models
by: Xu, Xiaoyu, et al.
Published: (2026)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
by: Gu, Tianle, et al.
Published: (2025)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
by: Li, Hao, et al.
Published: (2025)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

Majority Bit-Aware Watermarking For Large Language Models
by: Xu, Jiahao, et al.
Published: (2025)

CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems
by: Wen, Yan, et al.
Published: (2025)