Image de couverture de livre

CLIOPATRA: Extracting Private Information from LLM Insights

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Annamalai, Meenatchi Sundaram Muthu Selva, De Cristofaro, Emiliano, Kairouz, Peter
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2024)

"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generation
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2024)

The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging
par: Ganev, Georgi, et autres
Publié: (2024)

The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Data
par: Ganev, Georgi, et autres
Publié: (2025)

Beyond the Crawl: Unmasking Browser Fingerprinting in Real User Interactions
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2025)

It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
par: Annamalai, Meenatchi Sundaram Muthu Selva
Publié: (2024)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2024)

Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy
par: Ganev, Georgi, et autres
Publié: (2025)

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2025)

A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2023)

Tight Auditing of Differential Privacy in MST and AIM
par: Ganev, Georgi, et autres
Publié: (2026)

A Unified Framework for Adversary-Aware Differential Privacy Bounds
par: Swanberg, Marika, et autres
Publié: (2025)

Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
par: Ganev, Georgi, et autres
Publié: (2023)

Synthetic Data: Methods, Use Cases, and Risks
par: De Cristofaro, Emiliano
Publié: (2023)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
par: Chen, Chaoran, et autres
Publié: (2026)

Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective
par: Ganev, Georgi, et autres
Publié: (2026)

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
par: Ganev, Georgi, et autres
Publié: (2023)

A Systematic Review of Federated Generative Models
par: Gargary, Ashkan Vedadi, et autres
Publié: (2024)

Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning
par: Ball, Marshall, et autres
Publié: (2024)

PROTEAN: Federated Intrusion Detection in Non-IID Environments through Prototype-Based Knowledge Sharing
par: Chennoufi, Sara, et autres
Publié: (2025)

What's on Your Mind? Exploring Privacy of Mental Health Apps
par: Georgiou, Chloe, et autres
Publié: (2026)

Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
par: Swanberg, Marika, et autres
Publié: (2025)

Differentially Private Stream Processing at Scale
par: Zhang, Bing, et autres
Publié: (2023)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
par: Ganev, Georgi, et autres
Publié: (2025)

ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
par: Hu, Yuzheng, et autres
Publié: (2025)

TUBERAIDER: Attributing Coordinated Hate Attacks on YouTube Videos to their Source Communities
par: Saeed, Mohammad Hammas, et autres
Publié: (2023)

Inferentially-Private Private Information
par: Wang, Shuaiqi, et autres
Publié: (2024)

Privacy-Preserving Instructions for Aligning Large Language Models
par: Yu, Da, et autres
Publié: (2024)

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
par: Shumailov, Ilia, et autres
Publié: (2025)

MAPLE: Metadata Augmented Private Language Evolution
par: Chien, Eli, et autres
Publié: (2026)

Urania: Differentially Private Insights into AI Use
par: Liu, Daogao, et autres
Publié: (2025)

Randomization Techniques to Mitigate the Risk of Copyright Infringement
par: Chen, Wei-Ning, et autres
Publié: (2024)

Resource Estimation of CGGI and CKKS scheme workloads on FracTLcore Computing Fabric
par: Ovichinnikov, Denis, et autres
Publié: (2025)

Exploring the limits of strong membership inference attacks on large language models
par: Hayes, Jamie, et autres
Publié: (2025)

How to Privately Tune Hyperparameters in Federated Learning? Insights from a Benchmark Study
par: Mitic, Natalija, et autres
Publié: (2024)

Winemaking: Extracting Essential Insights for Efficient Threat Detection in Audit Logs
par: Wu, Weiheng, et autres
Publié: (2024)

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
par: Chen, Wei-Ning, et autres
Publié: (2024)

CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
par: Pentyala, Sikha, et autres
Publié: (2024)

Releasing Large-Scale Human Mobility Histograms with Differential Privacy
par: Bian, Christopher, et autres
Publié: (2024)

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
par: Zeng, Wenxuan, et autres
Publié: (2025)