Copertina

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schuchardt, Jan, Stoian, Mihail, Kosmala, Arthur, Günnemann, Stephan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
di: Schuchardt, Jan, et al.
Pubblicazione: (2025)

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
di: Schuchardt, Jan, et al.
Pubblicazione: (2023)

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
di: Saxena, Aman, et al.
Pubblicazione: (2026)

Privacy Amplification for Matrix Mechanisms
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2023)

Amplified Patch-Level Differential Privacy for Free via Random Cropping
di: Durmaz, Kaan, et al.
Pubblicazione: (2026)

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
di: Schuchardt, Jan, et al.
Pubblicazione: (2026)

Privacy Amplification for the Gaussian Mechanism via Bounded Support
di: Hu, Shengyuan, et al.
Pubblicazione: (2024)

Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling
di: Zhou, Felix
Pubblicazione: (2025)

Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration
di: Pierquin, Clément, et al.
Pubblicazione: (2023)

Personalized Privacy Amplification via Importance Sampling
di: Fay, Dominik, et al.
Pubblicazione: (2023)

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
di: Dong, Andy, et al.
Pubblicazione: (2025)

Privacy Amplification Through Synthetic Data: Insights from Linear Regression
di: Pierquin, Clément, et al.
Pubblicazione: (2025)

Privacy Amplification for BandMF via $b$-Min-Sep Subsampling
di: Dong, Andy, et al.
Pubblicazione: (2026)

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

Adversarial Attacks on Graph Neural Networks via Meta Learning
di: Zügner, Daniel, et al.
Pubblicazione: (2019)

Mitigating Error Amplification in Fast Adversarial Training
di: Zhao, Mengnan, et al.
Pubblicazione: (2026)

Privacy Amplification Persists under Unlimited Synthetic Data Release
di: Pierquin, Clément, et al.
Pubblicazione: (2026)

Detecting Adversarial Data via Provable Adversarial Noise Amplification
di: Mumcu, Furkan, et al.
Pubblicazione: (2026)

Near Exact Privacy Amplification for Matrix Mechanisms
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2024)

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
di: Cyffers, Edwige, et al.
Pubblicazione: (2022)

Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
di: Lebeda, Christian Janos, et al.
Pubblicazione: (2024)

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
di: Zhang, Boyang, et al.
Pubblicazione: (2024)

Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
di: Coalson, Zachary, et al.
Pubblicazione: (2026)

Privacy Amplification via Shuffling: Unified, Simplified, and Tightened
di: Wang, Shaowei, et al.
Pubblicazione: (2023)

Fast Proxies for LLM Robustness Evaluation
di: Beyer, Tim, et al.
Pubblicazione: (2025)

Calibrating Noise for Group Privacy in Subsampled Mechanisms
di: Jiang, Yangfan, et al.
Pubblicazione: (2024)

Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
di: Frery, Jordan, et al.
Pubblicazione: (2025)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
di: Sabanayagam, Mahalakshmi, et al.
Pubblicazione: (2024)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
di: Gosch, Lukas, et al.
Pubblicazione: (2024)

On the Alignment of Group Fairness with Attribute Privacy
di: Aalmoes, Jan, et al.
Pubblicazione: (2022)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
di: Wang, Linlin, et al.
Pubblicazione: (2025)

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems
di: Rahman, Md Hafizur, et al.
Pubblicazione: (2026)

Blockchain Amplification Attack
di: Tsuchiya, Taro, et al.
Pubblicazione: (2024)

Efficient Adversarial Training in LLMs with Continuous Attacks
di: Xhonneux, Sophie, et al.
Pubblicazione: (2024)

Practical Differentially Private Hyperparameter Tuning with Subsampling
di: Koskela, Antti, et al.
Pubblicazione: (2023)

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
di: Park, Seong-Gyu, et al.
Pubblicazione: (2026)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
di: Dong, Andy, et al.
Pubblicazione: (2026)

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
di: Räisä, Ossi, et al.
Pubblicazione: (2024)

On the Privacy of Selection Mechanisms with Gaussian Noise
di: Lebensold, Jonathan, et al.
Pubblicazione: (2024)

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
di: Khattar, Vanshaj, et al.
Pubblicazione: (2026)