paper-with-me

Papers

Fundamental Limits of Obfuscation for Linear Gaussian Dynamical Systems: An Information-Theoretic Approach

2020-10-29 · Song Fang, Quanyan Zhu

In this paper, we study the fundamental limits of obfuscation in terms of privacy-distortion tradeoffs for linear Gaussian dynamical systems via an information-theoretic approach. Particularly, we obtain analytical formulas that capture the fundamental privacy-distortion tradeoffs when privacy masks are to be added to the outputs of the dynamical systems, while indicating explicitly how to design the privacy masks in an optimal way: The privacy masks should be colored Gaussian with power spectra shaped specifically based upon the system and noise properties.

📄 PDF Abstract BibTeX arXiv:2011.00718

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems

2025-02-22 · Xintong Wang, Xiaofei Guan, Ling Guo, Hao Wu

Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems is a fundamental yet challenging problem in many fields of science and engineering. Existing methods face significant obstacles: Gaussian-bas…

Density Estimation

Metric-Entropy Limits on the Approximation of Nonlinear Dynamical Systems

2024-07-01 · Yang Pan, Clemens Hutter, Helmut Bölcskei

This paper is concerned with fundamental limits on the approximation of nonlinear dynamical systems. Specifically, we show that recurrent neural networks (RNNs) can approximate nonlinear systems -- that satisfy a Lipschi…

Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods

2022-12-27 · Alexander Shevchenko, Kevin Kögler, Hamed Hassani, Marco Mondelli

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain …

Data Compression

Channel Leakage, Information-Theoretic Limitations of Obfuscation, and Optimal Privacy Mask Design for Streaming Data

2020-08-11 · Song Fang, Quanyan Zhu

In this paper, we first introduce the notion of channel leakage as the minimum mutual information between the channel input and channel output. As its name indicates, channel leakage quantifies the minimum information le…

Obfuscated Activations Bypass LLM Latent-Space Defenses

2024-12-12 · Luke Bailey, Alex Serrano, Abhay Sheshadri, Mikhail Seleznyov 외

Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lead to undesirable actions. This prompts t…