Copertina

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shejwalkar, Virat, Ganesh, Arun, Mathews, Rajiv, Mu, Yarong, Song, Shuang, Thakkar, Om, Thakurta, Abhradeep, Zheng, Xinyi
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
di: Liu, Hongbin, et al.
Pubblicazione: (2024)

On Design Principles for Private Adaptive Optimizers
di: Ganesh, Arun, et al.
Pubblicazione: (2025)

Training Large ASR Encoders with Differential Privacy
di: Chauhan, Geeticka, et al.
Pubblicazione: (2024)

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2024)

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach
di: Ganesh, Arun, et al.
Pubblicazione: (2025)

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

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

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2023)

Multilingual and Multi-Accent Jailbreaking of Audio LLMs
di: Roh, Jaechul, et al.
Pubblicazione: (2025)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
di: Brown, Gavin, et al.
Pubblicazione: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
di: Steinke, Thomas, et al.
Pubblicazione: (2024)

Differentially Private Stream Processing at Scale
di: Zhang, Bing, et al.
Pubblicazione: (2023)

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
di: Vinod, Vishnu, et al.
Pubblicazione: (2025)

Correlated Noise Mechanisms for Differentially Private Learning
di: Pillutla, Krishna, et al.
Pubblicazione: (2025)

Decoding FL Defenses: Systemization, Pitfalls, and Remedies
di: Khan, Momin Ahmad, et al.
Pubblicazione: (2025)

Tighter Privacy Analysis for Truncated Poisson Sampling
di: Ganesh, Arun
Pubblicazione: (2025)

Preserving Expert-Level Privacy in Offline Reinforcement Learning
di: Sharma, Navodita, et al.
Pubblicazione: (2024)

Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
di: Gorantala, Shruthi, et al.
Pubblicazione: (2026)

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

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
di: Ganesh, Arun
Pubblicazione: (2024)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
di: Dvijotham, Krishnamurthy, et al.
Pubblicazione: (2024)

Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping
di: Wang, Lun, et al.
Pubblicazione: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
di: Nasr, Milad, et al.
Pubblicazione: (2025)

Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation
di: Maddock, Samuel, et al.
Pubblicazione: (2025)

ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
di: Zheng, Yusheng, et al.
Pubblicazione: (2026)

Inferentially-Private Private Information
di: Wang, Shuaiqi, et al.
Pubblicazione: (2024)

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
di: Cummings, Rachel, et al.
Pubblicazione: (2023)

Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis via Intermediate Representation and Language Model
di: Liu, Side, et al.
Pubblicazione: (2025)

Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization
di: Tran, Linh, et al.
Pubblicazione: (2026)

DCS Chain: A Flexible Private Blockchain System
di: Zheng, Jianwu, et al.
Pubblicazione: (2024)

Defense Against Prompt Injection Attack by Leveraging Attack Techniques
di: Chen, Yulin, et al.
Pubblicazione: (2024)

Whose Narrative is it Anyway? A KV Cache Manipulation Attack
di: Ganesh, Mukkesh, et al.
Pubblicazione: (2025)

PRIVMARK: Private Large Language Models Watermarking with MPC
di: Fargues, Thomas, et al.
Pubblicazione: (2025)

DPDSyn: Improving Differentially Private Dataset Synthesis for Model Training by Downstream Task Guidance
di: Jia, Mingxuan, et al.
Pubblicazione: (2026)

PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN
di: Zheng, Fei, et al.
Pubblicazione: (2024)

Encrypted Federated Search Using Homomorphic Encryption
di: Rathod, Om, et al.
Pubblicazione: (2025)

Kangaroo: A Private and Amortized Inference Framework over WAN for Large-Scale Decision Tree Evaluation
di: Xu, Wei, et al.
Pubblicazione: (2025)

Improving Count-Mean Sketch as the Leading Locally Differentially Private Frequency Estimator for Large Dictionaries
di: Pan, Mingen
Pubblicazione: (2024)

Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization
di: Xu, Shuangqing, et al.
Pubblicazione: (2025)

Locally Differentially Private In-Context Learning
di: Zheng, Chunyan, et al.
Pubblicazione: (2024)