Buchumschlag

Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Yanming, Eichler, Cédric, Anciaux, Nicolas, Bensamoun, Alexandra, Manzano, Lorena Gonzalez, Ghozzi, Seifeddine
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
von: Eichler, Cédric, et al.
Veröffentlicht: (2024)

LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs
von: Ibanez-Lissen, Luis, et al.
Veröffentlicht: (2025)

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
von: Ibanez-Lissen, Luis, et al.
Veröffentlicht: (2024)

Data Quality Issues in Vulnerability Detection Datasets
von: Guo, Yuejun, et al.
Veröffentlicht: (2024)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
von: Li, Yansong, et al.
Veröffentlicht: (2023)

ForensiBlock: A Provenance-Driven Blockchain Framework for Data Forensics and Auditability
von: Akbarfam, Asma Jodeiri, et al.
Veröffentlicht: (2023)

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis
von: Wang, Jianwei, et al.
Veröffentlicht: (2025)

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning
von: Lycklama, Hidde, et al.
Veröffentlicht: (2024)

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
von: Zhou, Tong, et al.
Veröffentlicht: (2024)

Onto-DP: Constructing Neighborhoods for Differential Privacy on Ontological Databases
von: Hayder, Yasmine, et al.
Veröffentlicht: (2026)

ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
von: Xie, Jin, et al.
Veröffentlicht: (2025)

PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
von: Liu, Yi, et al.
Veröffentlicht: (2025)

Differentially Private Subspace Fine-Tuning for Large Language Models
von: Zheng, Lele, et al.
Veröffentlicht: (2026)

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

Watermarking Text Data on Large Language Models for Dataset Copyright
von: Liu, Yixin, et al.
Veröffentlicht: (2023)

Model Provenance Testing for Large Language Models
von: Nikolic, Ivica, et al.
Veröffentlicht: (2025)

Revisiting Data Auditing in Large Vision-Language Models
von: Zhu, Hongyu, et al.
Veröffentlicht: (2025)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
von: Chen, Chaoran, et al.
Veröffentlicht: (2026)

FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMs
von: Wei, Zhiyuan, et al.
Veröffentlicht: (2024)

P3GNN: A Privacy-Preserving Provenance Graph-Based Model for APT Detection in Software Defined Networking
von: Nazari, Hedyeh, et al.
Veröffentlicht: (2024)

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
von: Qu, Wenjie, et al.
Veröffentlicht: (2025)

Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System
von: Dobrovolskyi, Ivan
Veröffentlicht: (2026)

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
von: Jin, Heng, et al.
Veröffentlicht: (2026)

FL-DECO-BC: A Privacy-Preserving, Provably Secure, and Provenance-Preserving Federated Learning Framework with Decentralized Oracles on Blockchain for VANETs
von: Narkedimilli, Sathwik, et al.
Veröffentlicht: (2024)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
von: Sha, Haichao, et al.
Veröffentlicht: (2026)

LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models
von: Mivule, Kato
Veröffentlicht: (2026)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
von: Afane, Mohamed, et al.
Veröffentlicht: (2025)

A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors
von: Xu, Zhenyu, et al.
Veröffentlicht: (2026)

NickPay, an Auditable, Privacy-Preserving, Nickname-Based Payment System
von: Quispe, Guillaume, et al.
Veröffentlicht: (2025)

Audit-or-Cast: Enforcing Honest Elections with Privacy-Preserving Public Verification
von: Rojjha, Aman, et al.
Veröffentlicht: (2026)

SilentLedger: Privacy-Preserving Auditing for Blockchains with Complete Non-Interactivity
von: Liu, Zihan, et al.
Veröffentlicht: (2025)

Auditing Private Prediction
von: Chadha, Karan, et al.
Veröffentlicht: (2024)

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models
von: Wei, Qianshan, et al.
Veröffentlicht: (2025)

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
von: Yi, Biao, et al.
Veröffentlicht: (2025)

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
von: Yoon, Jeongho, et al.
Veröffentlicht: (2026)

Fine-Tuning Foundation Models with Federated Learning for Privacy Preserving Medical Time Series Forecasting
von: Ali, Mahad, et al.
Veröffentlicht: (2025)

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

Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints
von: Bonhomme, Cedric, et al.
Veröffentlicht: (2026)

Where Trust Fails: Mapping Location-Data Provenance Risks in Europe
von: Brito, Eduardo, et al.
Veröffentlicht: (2026)

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
von: Zhang, Hao, et al.
Veröffentlicht: (2025)