Image de couverture de livre

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Du, Yanrui, Zhao, Sendong, Cao, Jiawei, Ma, Ming, Zhao, Danyang, Qi, Shuren, Fan, Fenglei, Liu, Ting, Qin, Bing
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
par: Du, Yanrui, et autres
Publié: (2025)

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
par: Du, Yanrui, et autres
Publié: (2025)

Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
par: Du, Yanrui, et autres
Publié: (2023)

Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
par: Du, Yanrui, et autres
Publié: (2023)

MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
par: Du, Yanrui, et autres
Publié: (2024)

MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
par: Guo, Haoqiang, et autres
Publié: (2024)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
par: Zhao, Weixiang, et autres
Publié: (2025)

Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification
par: Wang, Haochun, et autres
Publié: (2023)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
par: Du, Yanrui, et autres
Publié: (2026)

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
par: Chen, Yuhan, et autres
Publié: (2023)

Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns
par: Zhao, Yang, et autres
Publié: (2024)

AS-ES Learning: Towards Efficient CoT Learning in Small Models
par: Xi, Nuwa, et autres
Publié: (2024)

Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
par: Qiang, Zewen, et autres
Publié: (2025)

SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation
par: Wang, Haochun, et autres
Publié: (2026)

From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
par: Du, Yanrui, et autres
Publié: (2026)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
par: Ruan, Zhiwen, et autres
Publié: (2026)

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
par: Lai, Song, et autres
Publié: (2025)

Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
par: Zhao, Yang, et autres
Publié: (2025)

Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis
par: Wang, Haochun, et autres
Publié: (2024)

LLMs May Perform MCQA by Selecting the Least Incorrect Option
par: Wang, Haochun, et autres
Publié: (2024)

Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
par: Wu, Di, et autres
Publié: (2024)

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
par: Hahm, Dongyoon, et autres
Publié: (2025)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
par: Ju, Yiming, et autres
Publié: (2024)

RECOST: External Knowledge Guided Data-efficient Instruction Tuning
par: Zhang, Qi, et autres
Publié: (2024)

EdgeFlowerTune: Evaluating Federated LLM Fine-Tuning Under Realistic Edge System Constraints
par: Geng, Jiaxiang, et autres
Publié: (2026)

MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views
par: Cai, Muzhen, et autres
Publié: (2024)

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
par: Zhao, Hao, et autres
Publié: (2024)

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning
par: Du, Xiaohu, et autres
Publié: (2024)

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
par: Gao, Chang, et autres
Publié: (2023)

Secure LLM Fine-Tuning via Safety-Aware Probing
par: Wu, Chengcan, et autres
Publié: (2025)

Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
par: Wang, Haochun, et autres
Publié: (2023)

META-RAG: Meta-Analysis-Inspired Evidence-Re-Ranking Method for Retrieval-Augmented Generation in Evidence-Based Medicine
par: Sun, Mengzhou, et autres
Publié: (2025)

M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
par: Zhao, Chunguang, et autres
Publié: (2025)

Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models
par: Ramakrishnan, Badrinath, et autres
Publié: (2025)

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning
par: Ye, Yangfan, et autres
Publié: (2025)

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
par: Liu, Yilun, et autres
Publié: (2023)

Data Diversity Matters for Robust Instruction Tuning
par: Bukharin, Alexander, et autres
Publié: (2023)

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning
par: Li, Ming, et autres
Publié: (2024)

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
par: Alajrami, Ahmed, et autres
Publié: (2025)

Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
par: Wang, Haochun, et autres
Publié: (2026)