Imagen de Portada

Rethinking Benchmarks for Differentially Private Image Classification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mokhtari, Sabrina, Kodeiri, Sara, Mohapatra, Shubhankar, Tramèr, Florian, Kamath, Gautam
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
por: Tramèr, Florian, et al.
Publicado: (2022)

DriftXpress: Faster Drifting Models via Projected RKHS Fields
por: Falahati, Ali, et al.
Publicado: (2026)

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
por: Zhang, Jie, et al.
Publicado: (2024)

Optimal Differentially Private Sampling of Unbounded Gaussians
por: Iverson, Valentio, et al.
Publicado: (2025)

Differentially Private Post-Processing for Fair Regression
por: Xian, Ruicheng, et al.
Publicado: (2024)

Private Mean Estimation with Person-Level Differential Privacy
por: Agarwal, Sushant, et al.
Publicado: (2024)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
por: Yu, Da, et al.
Publicado: (2022)

Differentially Private Data Generation with Missing Data
por: Mohapatra, Shubhankar, et al.
Publicado: (2023)

Not All Learnable Distribution Classes are Privately Learnable
por: Bun, Mark, et al.
Publicado: (2024)

Differentially Private Optimization with Sparse Gradients
por: Ghazi, Badih, et al.
Publicado: (2024)

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
por: Feng, Shanglun, et al.
Publicado: (2024)

The Discrete Gaussian for Differential Privacy
por: Canonne, Clément L., et al.
Publicado: (2020)

Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph
por: Kamath, Gautam, et al.
Publicado: (2025)

The Broader Landscape of Robustness in Algorithmic Statistics
por: Kamath, Gautam
Publicado: (2024)

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
por: Liu, Peihan, et al.
Publicado: (2026)

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
por: Gu, Xin, et al.
Publicado: (2023)

CoinPress: Practical Private Mean and Covariance Estimation
por: Biswas, Sourav, et al.
Publicado: (2020)

Universal Jailbreak Backdoors from Poisoned Human Feedback
por: Rando, Javier, et al.
Publicado: (2023)

On the Learnability of Distribution Classes with Adaptive Adversaries
por: Lechner, Tosca, et al.
Publicado: (2025)

Learning to Inject: Automated Prompt Injection via Reinforcement Learning
por: Chen, Xin, et al.
Publicado: (2026)

Evading Black-box Classifiers Without Breaking Eggs
por: Debenedetti, Edoardo, et al.
Publicado: (2023)

Adversarial Search Engine Optimization for Large Language Models
por: Nestaas, Fredrik, et al.
Publicado: (2024)

Evaluations of Machine Learning Privacy Defenses are Misleading
por: Aerni, Michael, et al.
Publicado: (2024)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
por: Carlini, Nicholas, et al.
Publicado: (2025)

Indiscriminate Data Poisoning Attacks on Neural Networks
por: Lu, Yiwei, et al.
Publicado: (2022)

Blind Baselines Beat Membership Inference Attacks for Foundation Models
por: Das, Debeshee, et al.
Publicado: (2024)

Differentially Private Fair Binary Classifications
por: Ghoukasian, Hrad, et al.
Publicado: (2024)

From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
por: Mercier, Dominique, et al.
Publicado: (2023)

Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs
por: Li, Zhengdao, et al.
Publicado: (2024)

Laundering AI Authority with Adversarial Examples
por: Zhang, Jie, et al.
Publicado: (2026)

Membership Inference Attacks on Sequence Models
por: Rossi, Lorenzo, et al.
Publicado: (2025)

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
por: Rando, Javier, et al.
Publicado: (2025)

Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications
por: Liu, Yanchen, et al.
Publicado: (2023)

Differentially Private Auditing Under Strategic Response
por: Burnat, Florian A. D.
Publicado: (2026)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
por: Cadet, Xavier F., et al.
Publicado: (2024)

Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
por: Wang, Shuaiqi, et al.
Publicado: (2025)

Pitfalls in Evaluating Language Model Forecasters
por: Paleka, Daniel, et al.
Publicado: (2025)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
por: Nikolić, Kristina, et al.
Publicado: (2025)

Differentially Private Conformal Prediction
por: Wu, Jiamei, et al.
Publicado: (2026)

Differentially Private Wasserstein Barycenters
por: Gu, Anming, et al.
Publicado: (2025)