Copertina

Retraining with Predicted Hard Labels Provably Increases Model Accuracy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Das, Rudrajit, Dhillon, Inderjit S., Epasto, Alessandro, Javanmard, Adel, Mao, Jieming, Mirrokni, Vahab, Sanghavi, Sujay, Zhong, Peilin
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

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

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

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

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

Smooth Anonymity for Sparse Graphs
di: Epasto, Alessandro, et al.
Pubblicazione: (2022)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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