paper-with-me

Papers

Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation

2022-11-01 · Kristian Georgiev, Samuel B. Hopkins

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant fraction of the samples they receive are adversarially corrupted. Since optimal mechanisms typically achieve these high success probabilities, our results imply that optimal private mechanisms for many basic statistics problems are robust. We investigate the consequences of this observation for both algorithms and computational complexity across different statistical problems. Assuming the Brennan-Bresler secret-leakage planted clique conjecture, we demonstrate a fundamental tradeoff between computational efficiency, privacy leakage, and success probability for sparse mean estimation. Private algorithms which match this tradeoff are not yet known -- we achieve that (up to polylogarithmic factors) in a polynomially-large range of parameters via the Sum-of-Squares method. To establish an information-computation gap for private sparse mean estimation, we also design new (exponential-time) mechanisms using fewer samples than efficient algorithms must use. Finally, we give evidence for privacy-induced information-computation gaps for several other statistics and learning problems, including PAC learning parity functions and estimation of the mean of a multivariate Gaussian.

📄 PDF Abstract BibTeX arXiv:2211.00724

Code (1)

kristian-georgiev/privacy-induces-robustness 공식 구현

Tasks

Computational EfficiencyPAC learning

Similar Papers 제목 키워드 기반

Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training

2025-07-02 · Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer 외

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, its reliance on large volumes of labeled data raises privacy and security concerns suc…

Data PoisoningGeneralization Bounds

Quantization in Federated Learning: Methods, Challenges and Future Directions

2026-06-25 · Farwa Ikram, Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino arxiv

Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and th…

Federated Learning

SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text

2021-10-12 · Hoang-Quoc Nguyen-Son, Seira Hidano, Kazuhide Fukushima, Shinsaku Kiyomoto

There are two cases describing how a classifier processes input text, namely, misclassification and correct classification. In terms of misclassified texts, a classifier handles the texts with both incorrect predictions …

Adversarial TextClassification

Differentially Private Reward Functions in Policy Synthesis for Markov Decision Processes

2023-09-21 · Alexander Benvenuti, Calvin Hawkins, Brandon Fallin, Bo Chen 외

Markov decision processes often seek to maximize a reward function, but onlookers may infer reward functions by observing the states and actions of such systems, revealing sensitive information. Therefore, in this paper …

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

2025-11-10 · Pukang Ye, Junwei Luo, Xiaolei Dong, Yunbo Yang arxiv

Data duplication within large-scale corpora often impedes large language models' (LLMs) performance and privacy. In privacy-concerned federated learning scenarios, conventional deduplication methods typically rely on tru…

Federated Learning