Imagen de Portada

Retraining with Predicted Hard Labels Provably Increases Model Accuracy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Das, Rudrajit, Dhillon, Inderjit S., Epasto, Alessandro, Javanmard, Adel, Mao, Jieming, Mirrokni, Vahab, Sanghavi, Sujay, Zhong, Peilin
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
por: Javanmard, Adel, et al.
Publicado: (2025)

Differentially Private Synthetic Data Release for Topics API Outputs
por: Dick, Travis, et al.
Publicado: (2025)

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
por: Epasto, Alessandro, et al.
Publicado: (2022)

Improving the Variance of Differentially Private Randomized Experiments through Clustering
por: Javanmard, Adel, et al.
Publicado: (2023)

Smooth Anonymity for Sparse Graphs
por: Epasto, Alessandro, et al.
Publicado: (2022)

Perturb-and-Project: Differentially Private Similarities and Marginals
por: Cohen-Addad, Vincent, et al.
Publicado: (2024)

Private Training & Data Generation by Clustering Embeddings
por: Zhou, Felix, et al.
Publicado: (2025)

Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model
por: Cummings, Rachel, et al.
Publicado: (2025)

Differentially Private Clustering in Data Streams
por: Epasto, Alessandro, et al.
Publicado: (2023)

Towards Quantifying the Preconditioning Effect of Adam
por: Das, Rudrajit, et al.
Publicado: (2024)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
por: Zhang, Xinwei, et al.
Publicado: (2024)

Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private Algorithms
por: Epasto, Alessandro, et al.
Publicado: (2026)

Sublinear Space Graph Algorithms in the Continual Release Model
por: Epasto, Alessandro, et al.
Publicado: (2024)

Scalable Private Partition Selection via Adaptive Weighting
por: Chen, Justin Y., et al.
Publicado: (2025)

Optimistic Rates for Learning from Label Proportions
por: Li, Gene, et al.
Publicado: (2024)

Graph Unlearning with Efficient Partial Retraining
por: Zhang, Jiahao, et al.
Publicado: (2024)

Geometric Median (GM) Matching for Robust Data Pruning
por: Acharya, Anish, et al.
Publicado: (2024)

Honesty is the Best Policy: On the Accuracy of Apple Privacy Labels Compared to Apps' Privacy Policies
por: Ali, Mir Masood, et al.
Publicado: (2023)

Hard-Label Cryptanalytic Extraction of Neural Network Models
por: Chen, Yi, et al.
Publicado: (2024)

Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
por: Ito, Akira, et al.
Publicado: (2025)

Understanding the Role of Training Data in Test-Time Scaling
por: Javanmard, Adel, et al.
Publicado: (2025)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
por: Javanmard, Adel, et al.
Publicado: (2026)

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
por: Javanmard, Adel, et al.
Publicado: (2024)

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
por: Liu, Zixuan, et al.
Publicado: (2025)

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
por: Liu, Jun, et al.
Publicado: (2026)

LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation
por: He, Ying, et al.
Publicado: (2024)

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

Provably Secure Steganography Based on List Decoding
por: Pang, Kaiyi, et al.
Publicado: (2026)

Provable Execution in Real-Time Embedded Systems
por: Neto, Antonio Joia, et al.
Publicado: (2025)

Adaptive Cybersecurity: Dynamically Retrainable Firewalls for Real-Time Network Protection
por: Ahmadi, Sina
Publicado: (2025)

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
por: Carlini, Nicholas, et al.
Publicado: (2024)

Scalable contribution bounding to achieve privacy
por: Cohen-Addad, Vincent, et al.
Publicado: (2025)

Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography
por: Zhu, Jiahao, et al.
Publicado: (2024)

Provably Robust and Secure Steganography in Asymmetric Resource Scenario
por: Bai, Minhao, et al.
Publicado: (2024)

Beyond Algorithmic Proofs: Towards Implementation-Level Provable Security
por: Shang, Jiahui, et al.
Publicado: (2025)

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
por: Nie, Chenfei, et al.
Publicado: (2024)

Provably Robust Multi-bit Watermarking for AI-generated Text
por: Qu, Wenjie, et al.
Publicado: (2024)

Towards Provably Secure Generative AI: Reliable Consensus Sampling
por: Cui, Yu, et al.
Publicado: (2025)

STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
por: Qi, Yuang, et al.
Publicado: (2026)

Asymmetric Mempool DoS Security: Formal Definitions and Provable Secure Designs
por: Ding, Wanning, et al.
Publicado: (2024)