Image de couverture de livre

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tong, Xin, Lin, Zhi, Wang, Jingya, Han, Meng, Jin, Bo
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
par: Yi, Biao, et autres
Publié: (2025)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
par: Liu, Tiantian, et autres
Publié: (2024)

Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
par: Xu, Zhenhua, et autres
Publié: (2024)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
par: Li, Yansong, et autres
Publié: (2023)

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
par: Wu, Jialin, et autres
Publié: (2025)

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?
par: Karkevandi, Mohammad Bahrami, et autres
Publié: (2024)

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
par: Zhou, Tong, et autres
Publié: (2024)

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
par: Yin, Rui, et autres
Publié: (2026)

Confidence Elicitation: A New Attack Vector for Large Language Models
par: Formento, Brian, et autres
Publié: (2025)

BadActs: A Universal Backdoor Defense in the Activation Space
par: Yi, Biao, et autres
Publié: (2024)

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage
par: Shao, Hanyin, et autres
Publié: (2023)

InfoFlood: Jailbreaking Large Language Models with Information Overload
par: Yadav, Advait, et autres
Publié: (2025)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
par: Yang, Qin, et autres
Publié: (2024)

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
par: Xu, Zhenhua, et autres
Publié: (2025)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
par: Wang, Haoran, et autres
Publié: (2023)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
par: Zhao, Yunhan, et autres
Publié: (2026)

Resource Consumption Red-Teaming for Large Vision-Language Models
par: Gao, Haoran, et autres
Publié: (2025)

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
par: Wang, Zilong, et autres
Publié: (2025)

Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
par: Zheng, JiaYing, et autres
Publié: (2024)

Lightweight Yet Secure: Secure Scripting Language Generation via Lightweight LLMs
par: Zhang, Keyang, et autres
Publié: (2026)

Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
par: Fu, Wenjie, et autres
Publié: (2023)

Denial-of-Service Poisoning Attacks against Large Language Models
par: Gao, Kuofeng, et autres
Publié: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
par: Yi, Biao, et autres
Publié: (2025)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
par: Zhang, Junbo, et autres
Publié: (2025)

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
par: Tang, Xinyu, et autres
Publié: (2024)

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
par: Yang, Guangyu, et autres
Publié: (2025)

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
par: Gu, Haoran, et autres
Publié: (2025)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
par: Wang, Zhepeng, et autres
Publié: (2024)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
par: Wu, Yu-Hang, et autres
Publié: (2025)

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
par: Yin, Haoteng, et autres
Publié: (2024)

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
par: Fan, Wei, et autres
Publié: (2024)

Analysing the Safety Pitfalls of Steering Vectors
par: Li, Yuxiao, et autres
Publié: (2026)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
par: Afane, Mohamed, et autres
Publié: (2025)

StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures
par: Li, Bangxin, et autres
Publié: (2024)

Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data
par: Li, Haoran, et autres
Publié: (2024)

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
par: Shen, Guobin, et autres
Publié: (2024)

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

Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
par: Chen, Yuetian, et autres
Publié: (2026)

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
par: Zhang, Yuyou, et autres
Publié: (2025)

Copyright Traps for Large Language Models
par: Meeus, Matthieu, et autres
Publié: (2024)