Cover Image

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qi, Weiwei, Wu, Zefeng, Zheng, Tianhang, Zhang, Zikang, Jia, Xiaojun, Qin, Zhan, Ren, Kui
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
by: Qi, Weiwei, et al.
Published: (2025)

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
by: Zeng, Churui, et al.
Published: (2026)

Untargeted Jailbreak Attack
by: Huang, Xinzhe, et al.
Published: (2025)

Dynamic Target Attack
by: Xiu, Kedong, et al.
Published: (2025)

DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
by: Huang, Xinzhe, et al.
Published: (2025)

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning
by: Ma, Binhao, et al.
Published: (2024)

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
by: He, Yu, et al.
Published: (2025)

ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
by: Xie, Jin, et al.
Published: (2025)

Membership Inference Attacks Against Vision-Language Models
by: Hu, Yuke, et al.
Published: (2025)

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

A Certified Robust Watermark For Large Language Models
by: Feng, Xianheng, et al.
Published: (2024)

Machine Unlearning in Large Language Models
by: Chen, Kongyang, et al.
Published: (2024)

FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
by: Yao, Hongwei, et al.
Published: (2023)

Peering Behind the Shield: Guardrail Identification in Large Language Models
by: Yang, Ziqing, et al.
Published: (2025)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
by: He, Yu, et al.
Published: (2025)

Functional Subspace Watermarking for Large Language Models
by: Ding, Zikang, et al.
Published: (2026)

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
by: Deng, Gelei, et al.
Published: (2023)

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
by: Teng, Ma, et al.
Published: (2024)

SWAT: A System-Wide Approach to Tunable Leakage Mitigation in Encrypted Data Stores
by: Zheng, Leqian, et al.
Published: (2023)

Permit: Permission-Aware Representation Intervention for Controlled Generation in Large Language Models
by: Sun, Pengcheng, et al.
Published: (2026)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
by: Zhao, Tianhang, et al.
Published: (2025)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
by: Shao, Shuo, et al.
Published: (2024)

SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
by: Ba, Zhongjie, et al.
Published: (2023)

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
by: Wang, Bo, et al.
Published: (2026)

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
by: Zhang, Hao, et al.
Published: (2025)

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
by: Liu, Guozhi, et al.
Published: (2025)

Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models
by: Nguyen, Hoang Cuong, et al.
Published: (2025)

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
by: Li, Songze, et al.
Published: (2026)

Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification
by: He, Yiling, et al.
Published: (2024)

PortGPT: Towards Automated Backporting Using Large Language Models
by: Li, Zhaoyang, et al.
Published: (2025)

FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis
by: He, Yiling, et al.
Published: (2023)

Towards Action Hijacking of Large Language Model-based Agent
by: Zhang, Yuyang, et al.
Published: (2024)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
by: Chen, Yulong, et al.
Published: (2025)

SpatialJB: How Text Distribution Art Becomes the "Jailbreak Key" for LLM Guardrails
by: Mou, Zhiyi, et al.
Published: (2026)

Towards Automated Pentesting with Large Language Models
by: Bessa, Ricardo, et al.
Published: (2026)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
by: Chen, Tailun, et al.
Published: (2025)

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
by: Xu, Huiyu, et al.
Published: (2024)

FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
by: Zheng, Tianhang, et al.
Published: (2024)

CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Models
by: Liu, Xiaoqun, et al.
Published: (2025)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
by: Ying, Zonghao, et al.
Published: (2024)