Cover Image

Adaptive Backtracking for Privacy Protection in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Zhihao, Gu, Yuxuan, Feng, Xiachong, Ma, Weitao, Li, Bo, Feng, Xiaocheng
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
by: Feng, Shanglun, et al.
Published: (2024)

Strong Copyright Protection for Language Models via Adaptive Model Fusion
by: Abad, Javier, et al.
Published: (2024)

DeepInception: Hypnotize Large Language Model to Be Jailbreaker
by: Li, Xuan, et al.
Published: (2023)

Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
by: Qian, Wei, et al.
Published: (2025)

Analysis of Privacy Leakage in Federated Large Language Models
by: Vu, Minh N., et al.
Published: (2024)

Machine Learning with Privacy for Protected Attributes
by: Mahloujifar, Saeed, et al.
Published: (2025)

Beyond Data Privacy: New Privacy Risks for Large Language Models
by: Du, Yuntao, et al.
Published: (2025)

Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models
by: Shi, Haonan, et al.
Published: (2025)

Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
by: Liu, Dancheng, et al.
Published: (2024)

Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks
by: Badidi, Ikhlasse, et al.
Published: (2025)

SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy
by: Nahid, Md Mahadi Hasan, et al.
Published: (2024)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
by: Rashid, Md Rafi Ur, et al.
Published: (2023)

Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
by: Akkus, Atilla, et al.
Published: (2024)

Does Training with Synthetic Data Truly Protect Privacy?
by: Zhao, Yunpeng, et al.
Published: (2025)

An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models
by: Ahmadi, Kasra, et al.
Published: (2025)

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models
by: Mohammad, Noor Islam S., et al.
Published: (2026)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

Adaptively Private Next-Token Prediction of Large Language Models
by: Flemings, James, et al.
Published: (2024)

A Survey on Privacy Risks and Protection in Large Language Models
by: Chen, Kang, et al.
Published: (2025)

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
by: Li, Zhangheng, et al.
Published: (2024)

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models
by: Jin, Heng, et al.
Published: (2024)

FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation
by: Gu, Yuechun, et al.
Published: (2024)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
by: Lou, Jiadong, et al.
Published: (2025)

Copyright-Protected Language Generation via Adaptive Model Fusion
by: Abad, Javier, et al.
Published: (2024)

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
by: Xiang, Zhen, et al.
Published: (2024)

Privacy Preserving Adaptive Experiment Design
by: Li, Jiachun, et al.
Published: (2024)

Empirical Calibration and Metric Differential Privacy in Language Models
by: Faustini, Pedro, et al.
Published: (2025)

CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering
by: Gaddi, Matilda, et al.
Published: (2026)

Effective and Efficient Cross-City Traffic Knowledge Transfer: A Privacy-Preserving Perspective
by: Zeng, Zhihao, et al.
Published: (2025)

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy
by: Aliakbarpour, Maryam, et al.
Published: (2024)

Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learning
by: Yang, Xue, et al.
Published: (2024)

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
by: Liu, Zhenlong, et al.
Published: (2024)

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
by: Li, Xianzhi, et al.
Published: (2024)

Calibrating Practical Privacy Risks for Differentially Private Machine Learning
by: Gu, Yuechun, et al.
Published: (2024)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
by: Huang, Catherine, et al.
Published: (2024)

Efficient Federated Unlearning with Adaptive Differential Privacy Preservation
by: Jiang, Yu, et al.
Published: (2024)

FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learning
by: Zeng, Zhihao, et al.
Published: (2025)

Learnable Privacy Neurons Localization in Language Models
by: Chen, Ruizhe, et al.
Published: (2024)