Imagen de Portada

Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Du, Hao, Liu, Shang, Cao, Yang
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
por: Huang, Tiansheng, et al.
Publicado: (2024)

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
por: Piran, Fardin Jalil, et al.
Publicado: (2024)

Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning
por: Li, Shen, et al.
Publicado: (2024)

AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs
por: Krishna, Varun Badrinath
Publicado: (2024)

ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
por: Frikha, Ahmed, et al.
Publicado: (2024)

Protect Your Score: Contact Tracing With Differential Privacy Guarantees
por: Romijnders, Rob, et al.
Publicado: (2023)

Improved Algorithms for Differentially Private Language Model Alignment
por: Chen, Keyu, et al.
Publicado: (2025)

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
por: Guo, Qiming, et al.
Publicado: (2025)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
por: Wang, Erchi, et al.
Publicado: (2026)

CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
por: Arachchige, Shashie Dilhara Batan, et al.
Publicado: (2025)

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
por: Li, Yuecheng, et al.
Publicado: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
por: Chu, Junjie, et al.
Publicado: (2024)

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
por: Ke, Shuqi, et al.
Publicado: (2024)

DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
por: Gao, Xinyu, et al.
Publicado: (2025)

SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
por: Zhang, Zhisheng, et al.
Publicado: (2025)

Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
por: Lowy, Andrew, et al.
Publicado: (2024)

Private Linear Regression with Differential Privacy and PAC Privacy
por: Yang, Hillary, et al.
Publicado: (2024)

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
por: Panebianco, Francesco, et al.
Publicado: (2025)

HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
por: Wang, Yuxin, et al.
Publicado: (2024)

Differentially Private Model Merging
por: Yin, Qichuan, et al.
Publicado: (2026)

Provable Privacy with Non-Private Pre-Processing
por: Hu, Yaxi, et al.
Publicado: (2024)

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
por: Panzade, Prajwal, et al.
Publicado: (2024)

Attack-Aware Noise Calibration for Differential Privacy
por: Kulynych, Bogdan, et al.
Publicado: (2024)

RAG with Differential Privacy
por: Grislain, Nicolas
Publicado: (2024)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
por: Kazdan, Joshua, et al.
Publicado: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
por: Changjiang, Li, et al.
Publicado: (2025)

Differentially Private Preference Data Synthesis for Large Language Model Alignment
por: Gao, Fengyu, et al.
Publicado: (2026)

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
por: Gao, Fengyu, et al.
Publicado: (2024)

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
por: Mehmood, Haaris, et al.
Publicado: (2026)

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
por: Sui, Zhihao, et al.
Publicado: (2025)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
por: Huang, Tiansheng, et al.
Publicado: (2025)

Attacks and Defenses Against LLM Fingerprinting
por: Kurian, Kevin, et al.
Publicado: (2025)

Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
por: Liu, Huikang, et al.
Publicado: (2026)

Differentially Private Worst-group Risk Minimization
por: Zhou, Xinyu, et al.
Publicado: (2024)

Privacy Assessment of Federated Learning using Private Personalized Layers
por: Jourdan, Théo, et al.
Publicado: (2021)

SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference
por: Mishra, Abhijit, et al.
Publicado: (2023)

Optimal Defenses Against Gradient Reconstruction Attacks
por: Chen, Yuxiao, et al.
Publicado: (2024)

Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes
por: Wu, Guanchen, et al.
Publicado: (2025)

Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
por: Wu, Ruihan, et al.
Publicado: (2025)

Protecting Private Code in IDE Autocomplete using Differential Privacy
por: Grigorenko, Evgeny, et al.
Publicado: (2026)