Image de couverture de livre

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ganesh, Arun, McMahan, Brendan, Nasr, Milad, Steinke, Thomas, Thakurta, Abhradeep
Format:	Preprint
Publié:	2025
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

On Design Principles for Private Adaptive Optimizers
par: Ganesh, Arun, et autres
Publié: (2025)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
par: Dvijotham, Krishnamurthy, et autres
Publié: (2024)

Privacy Amplification for Matrix Mechanisms
par: Choquette-Choo, Christopher A., et autres
Publié: (2023)

Near Exact Privacy Amplification for Matrix Mechanisms
par: Choquette-Choo, Christopher A., et autres
Publié: (2024)

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
par: Choquette-Choo, Christopher A., et autres
Publié: (2024)

Correlated Noise Mechanisms for Differentially Private Learning
par: Pillutla, Krishna, et autres
Publié: (2025)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
par: Steinke, Thomas, et autres
Publié: (2024)

Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
par: Liu, Hongbin, et autres
Publié: (2024)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
par: Choquette-Choo, Christopher A., et autres
Publié: (2023)

An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy
par: McMahan, H. Brendan, et autres
Publié: (2025)

Training Large ASR Encoders with Differential Privacy
par: Chauhan, Geeticka, et autres
Publié: (2024)

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
par: Shejwalkar, Virat, et autres
Publié: (2022)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
par: Vinod, Vishnu, et autres
Publié: (2025)

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

Fine-Tuning Large Language Models with User-Level Differential Privacy
par: Charles, Zachary, et autres
Publié: (2024)

Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
par: Gorantala, Shruthi, et autres
Publié: (2026)

Remote Timing Attacks on Efficient Language Model Inference
par: Carlini, Nicholas, et autres
Publié: (2024)

One-shot Empirical Privacy Estimation for Federated Learning
par: Andrew, Galen, et autres
Publié: (2023)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
par: Brown, Gavin, et autres
Publié: (2024)

Next Generation of Phishing Attacks using AI powered Browsers
par: Arun, Akshaya, et autres
Publié: (2024)

Tighter Privacy Analysis for Truncated Poisson Sampling
par: Ganesh, Arun
Publié: (2025)

Federated Learning in Practice: Reflections and Projections
par: Daly, Katharine, et autres
Publié: (2024)

Preserving Expert-Level Privacy in Offline Reinforcement Learning
par: Sharma, Navodita, et autres
Publié: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
par: Nasr, Milad, et autres
Publié: (2025)

Privacy Amplification for BandMF via $b$-Min-Sep Subsampling
par: Dong, Andy, et autres
Publié: (2026)

Optimal Attack and Defense for Reinforcement Learning
par: McMahan, Jeremy, et autres
Publié: (2023)

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
par: Ganesh, Arun
Publié: (2024)

Stealing Part of a Production Language Model
par: Carlini, Nicholas, et autres
Publié: (2024)

Auditing Private Prediction
par: Chadha, Karan, et autres
Publié: (2024)

Inception: Efficiently Computable Misinformation Attacks on Markov Games
par: McMahan, Jeremy, et autres
Publié: (2024)

On Computational Indistinguishability and Logical Relations
par: Lago, Ugo Dal, et autres
Publié: (2024)

Data Poisoning to Fake a Nash Equilibrium in Markov Games
par: Wu, Young, et autres
Publié: (2023)

Cascading Adversarial Bias from Injection to Distillation in Language Models
par: Chaudhari, Harsh, et autres
Publié: (2025)

How to Use Quantum Indistinguishability Obfuscation
par: Coladangelo, Andrea, et autres
Publié: (2023)

Evaluating the Indistinguishability of Logic Locking using K-Cut Enumeration and Boolean Matching
par: Cruz, Jonathan, et autres
Publié: (2026)

Confidential Federated Computations
par: Eichner, Hubert, et autres
Publié: (2024)

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
par: Huang, Yangsibo, et autres
Publié: (2024)

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
par: Tang, Xinyu, et autres
Publié: (2024)

Simultaneous Haar Indistinguishability with Applications to Unclonable Cryptography
par: Ananth, Prabhanjan, et autres
Publié: (2024)

Detection of Dark Web Threats Using Machine Learning and Image Processing
par: Medipelly, Swetha, et autres
Publié: (2024)