Image de couverture de livre

Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Tiansheng, Hu, Sihao, Ilhan, Fatih, Tekin, Selim Furkan, Liu, Ling
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
par: Huang, Tiansheng, et autres
Publié: (2024)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
par: Huang, Tiansheng, et autres
Publié: (2025)

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
par: Huang, Tiansheng, et autres
Publié: (2024)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
par: Huang, Tiansheng, et autres
Publié: (2024)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
par: Huang, Tiansheng, et autres
Publié: (2025)

LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity
par: Tekin, Selim Furkan, et autres
Publié: (2024)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
par: Tekin, Selim Furkan, et autres
Publié: (2024)

Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
par: Tekin, Selim Furkan, et autres
Publié: (2024)

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
par: Liu, Guozhi, et autres
Publié: (2025)

Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
par: Ilhan, Fatih, et autres
Publié: (2026)

Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation
par: Liu, Guozhi, et autres
Publié: (2024)

MELT: A Behavioral Trace Dataset for High-Risk Memecoin Launch Detection
par: Hu, Sihao, et autres
Publié: (2026)

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
par: Huang, Tiansheng, et autres
Publié: (2024)

A Survey on Large Language Model-Based Game Agents
par: Hu, Sihao, et autres
Publié: (2024)

Adversarial Attention Perturbations for Large Object Detection Transformers
par: Yahn, Zachary, et autres
Publié: (2025)

FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients
par: Ilhan, Fatih, et autres
Publié: (2025)

Personalized Face Privacy Protection From a Single Image
par: Yahn, Zachary, et autres
Publié: (2026)

A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
par: Xu, Yichang, et autres
Publié: (2026)

PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
par: Hu, Sihao, et autres
Publié: (2024)

Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
par: Tekin, Selim Furkan, et autres
Publié: (2025)

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

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
par: Hu, Zixuan, et autres
Publié: (2025)

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
par: Li, Xiangman, et autres
Publié: (2025)

A Neurosymbolic Agent System for Compositional Visual Reasoning
par: Xu, Yichang, et autres
Publié: (2025)

Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment
par: Ding, Sihao
Publié: (2026)

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
par: Youstra, Jack, et autres
Publié: (2025)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
par: Sun, Yan, et autres
Publié: (2025)

Lazy Data Practices Harm Fairness Research
par: Simson, Jan, et autres
Publié: (2024)

Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
par: Hsu, Chia-Yi, et autres
Publié: (2024)

Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning
par: Tekin, Selim Furkan, et autres
Publié: (2026)

Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge
par: Huang, Yuan
Publié: (2025)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
par: Chen, Pin-Yu, et autres
Publié: (2025)

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
par: Wang, Jingtan, et autres
Publié: (2024)

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

Fine-tuning Large Language Model for Automated Algorithm Design
par: Liu, Fei, et autres
Publié: (2025)

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
par: Li, Yuxi, et autres
Publié: (2024)

A Study of Optimizations for Fine-tuning Large Language Models
par: Singh, Arjun, et autres
Publié: (2024)

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
par: Nguyen, Quoc Minh, et autres
Publié: (2026)

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
par: Wang, Yibo, et autres
Publié: (2025)

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
par: Huang, Kai, et autres
Publié: (2023)