Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chendi, Zhu, Yuqing, Su, Weijie J., Wang, Yu-Xiang
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
by: Li, Xiang, et al.
Published: (2025)

A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
by: Su, Weijie J.
Published: (2024)

The 2020 US Decennial Census is more private than you (might) think
by: Su, Buxin, et al.
Published: (2024)

PrivCode: When Code Generation Meets Differential Privacy
by: Liu, Zheng, et al.
Published: (2025)

Belt and Braces: When Federated Learning Meets Differential Privacy
by: Ren, Xuebin, et al.
Published: (2024)

PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps
by: Liu, Ruixuan, et al.
Published: (2024)

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
by: Zhu, Sichen, et al.
Published: (2025)

Network-Aware Differential Privacy
by: Li, Zhou, et al.
Published: (2025)

SemDP: Semantic-level Differential Privacy Protection for Face Datasets
by: Zhang, Xiaoting, et al.
Published: (2024)

Purifying Approximate Differential Privacy with Randomized Post-processing
by: Lin, Yingyu, et al.
Published: (2025)

Subgraph Counting under Edge Local Differential Privacy Based on Noisy Adjacency Matrix
by: Guo, Jintao, et al.
Published: (2025)

Shifted Interpolation for Differential Privacy
by: Bok, Jinho, et al.
Published: (2024)

Differentially Private Spatiotemporal Trajectory Synthesis with Retained Data Utility
by: Ge, Yuqing, et al.
Published: (2024)

Enhancing Noisy Functional Encryption for Privacy-Preserving Machine Learning
by: Scheu-Hachtel, Linda, et al.
Published: (2025)

RAIN: Secure and Robust Aggregation under Shuffle Model of Differential Privacy
by: Li, Yuhang, et al.
Published: (2026)

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
by: Redberg, Rachel, et al.
Published: (2023)

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

Curator Attack: When Blackbox Differential Privacy Auditing Loses Its Power
by: Wang, Shiming, et al.
Published: (2024)

Epass: Efficient and Privacy-Preserving Asynchronous Payment on Blockchain
by: Wang, Weijie, et al.
Published: (2025)

Local Differential Privacy for Tensors in Distributed Computing Systems
by: Yuan, Yachao, et al.
Published: (2025)

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy
by: Wu, Ruihan, et al.
Published: (2025)

Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
by: Wang, Hua, et al.
Published: (2022)

Advances in Differential Privacy and Differentially Private Machine Learning
by: Das, Saswat, et al.
Published: (2024)

Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
by: Yang, Yilin, et al.
Published: (2023)

Bridging Quantum Computing and Differential Privacy: Insights into Quantum Computing Privacy
by: Zhao, Yusheng, et al.
Published: (2024)

FedFDP: Fairness-Aware Federated Learning with Differential Privacy
by: Ling, Xinpeng, et al.
Published: (2024)

Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation
by: Wang, Yuchen, et al.
Published: (2024)

Benchmarking Secure Sampling Protocols for Differential Privacy
by: Fu, Yucheng, et al.
Published: (2024)

Towards Differential Privacy in Sequential Recommendation: A Noisy Graph Neural Network Approach
by: Hu, Wentao, et al.
Published: (2023)

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

Gait-Based Privacy Protection for Smart Wearable Devices
by: Su, Yu, et al.
Published: (2024)

Preserving Node-level Privacy in Graph Neural Networks
by: Xiang, Zihang, et al.
Published: (2023)

A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
by: Li, Xiang, et al.
Published: (2025)

Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
by: Bai, Shaojie, et al.
Published: (2024)

A Novel Approach to Differential Privacy with Alpha Divergence
by: Liu, Yifeng, et al.
Published: (2025)

Private Means and the Curious Incident of the Free Lunch
by: Fitzsimons, Jack, et al.
Published: (2024)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
by: Wang, Weiqi, et al.
Published: (2025)

Approximate Differential Privacy of the $\ell_2$ Mechanism
by: Joseph, Matthew, et al.
Published: (2025)

Local Distance Query with Differential Privacy
by: Sheng, Weihong, et al.
Published: (2025)

Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy
by: Riess, Anneliese, et al.
Published: (2026)