Copertina

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chien, Eli, Li, Pan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
di: Liang, Hao, et al.
Pubblicazione: (2025)

Certified Machine Unlearning via Noisy Stochastic Gradient Descent
di: Chien, Eli, et al.
Pubblicazione: (2024)

Differentially Private Relational Learning with Entity-level Privacy Guarantees
di: Huang, Yinan, et al.
Pubblicazione: (2025)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
di: Sha, Haichao, et al.
Pubblicazione: (2023)

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

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
di: Greenewald, Kristjan, et al.
Pubblicazione: (2024)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
di: Feng, Ce, et al.
Pubblicazione: (2024)

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
di: Ertan, Murat Bilgehan, et al.
Pubblicazione: (2026)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
di: Cebere, Tudor, et al.
Pubblicazione: (2024)

On the Convergence of DP-SGD with Adaptive Clipping
di: Shulgin, Egor, et al.
Pubblicazione: (2024)

Differentially Private Graph Diffusion with Applications in Personalized PageRanks
di: Wei, Rongzhe, et al.
Pubblicazione: (2024)

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls
di: Prakash, Saurav, et al.
Pubblicazione: (2023)

Convergent Differential Privacy Analysis for General Federated Learning
di: Sun, Yan, et al.
Pubblicazione: (2024)

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
di: Yin, Haoteng, et al.
Pubblicazione: (2024)

Expressive Losses for Verified Robustness via Convex Combinations
di: De Palma, Alessandro, et al.
Pubblicazione: (2023)

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
di: Wu, Jiapeng, et al.
Pubblicazione: (2023)

Have it your way: Individualized Privacy Assignment for DP-SGD
di: Boenisch, Franziska, et al.
Pubblicazione: (2023)

DP-SGD with weight clipping
di: Barczewski, Antoine, et al.
Pubblicazione: (2023)

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
di: Liu, Zheyuan, et al.
Pubblicazione: (2023)

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
di: Wang, Erchi, et al.
Pubblicazione: (2026)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
di: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Pubblicazione: (2024)

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
di: Romijnders, Rob, et al.
Pubblicazione: (2024)

PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
di: Kazmi, Mishaal, et al.
Pubblicazione: (2024)

A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
di: Zhao, Puning, et al.
Pubblicazione: (2024)

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
di: Ravikumar, Deepak, et al.
Pubblicazione: (2024)

R+R:Understanding Hyperparameter Effects in DP-SGD
di: Morsbach, Felix, et al.
Pubblicazione: (2024)

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
di: Feng, Shuya, et al.
Pubblicazione: (2024)

An Efficient Difference-of-Convex Solver for Privacy Funnel
di: Huang, Teng-Hui, et al.
Pubblicazione: (2024)

DP-Dueling: Learning from Preference Feedback without Compromising User Privacy
di: Saha, Aadirupa, et al.
Pubblicazione: (2024)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
di: Wei, Jianxin, et al.
Pubblicazione: (2022)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
di: Bethune, Louis, et al.
Pubblicazione: (2023)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
di: Wei, Chengkun, et al.
Pubblicazione: (2025)

Metric Privacy in Federated Learning for Medical Imaging: Improving Convergence and Preventing Client Inference Attacks
di: Díaz, Judith Sáinz-Pardo, et al.
Pubblicazione: (2025)

Closed-Form Bounds for DP-SGD against Record-level Inference
di: Cherubin, Giovanni, et al.
Pubblicazione: (2024)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
di: Zhang, Xinwei, et al.
Pubblicazione: (2023)

Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
di: Zhou, Yvonne, et al.
Pubblicazione: (2026)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
di: Wang, Liangyu, et al.
Pubblicazione: (2025)

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