paper-with-me

홈 › Papers

Efficiently Learning Any One Hidden Layer ReLU Network From Queries

2021-11-08 · Sitan Chen, Adam R Klivans, Raghu Meka

Model extraction attacks have renewed interest in the classic problem of learning neural networks from queries. In this work we give the first polynomial-time algorithm for learning arbitrary one hidden layer neural networks activations provided black-box access to the network. Formally, we show that if $F$ is an arbitrary one hidden layer neural network with ReLU activations, there is an algorithm with query complexity and running time that is polynomial in all parameters that outputs a network $F'$ achieving low square loss relative to $F$ with respect to the Gaussian measure. While a number of works in the security literature have proposed and empirically demonstrated the effectiveness of certain algorithms for this problem, ours is the first with fully polynomial-time guarantees of efficiency even for worst-case networks (in particular our algorithm succeeds in the overparameterized setting).

📄 PDF Abstract BibTeX arXiv:2111.04727

Code (0)

등록된 구현이 없습니다.

Tasks

Model extraction

Similar Papers 제목 키워드 기반

Efficiently Learning One Hidden Layer ReLU Networks From Queries

2021-12-01 · NeurIPS 2021 12 · Sitan Chen, Adam Klivans, Raghu Meka

While the problem of PAC learning neural networks from samples has received considerable attention in recent years, in certain settings like model extraction attacks, it is reasonable to imagine having more than just the…

Model extractionPAC learning

Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks

2022-02-10 · Sitan Chen, Aravind Gollakota, Adam R. Klivans, Raghu Meka

We give superpolynomial statistical query (SQ) lower bounds for learning two-hidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free) model. No general SQ lower bounds were known for learni…

PAC learningVocal Bursts Valence Prediction

On the Principles of Deep Feedforward ReLU Networks

2026-07-08 · Changcun Huang arxiv

The architecture of deep feedforward neural networks is ubiquitous in deep learning, either as a whole system or as a subnetwork of other architectures, and thus its mechanism is a key ingredient of the black box of neur…

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting

2024-10-08 · Nicholas Carlini, Jorge Chávez-Saab, Anna Hambitzer, Francisco Rodríguez-Henríquez 외

Deep neural networks (DNNs) are valuable assets, yet their public accessibility raises security concerns about parameter extraction by malicious actors. Recent work by Carlini et al. (crypto'20) and Canales-Mart\'inez et…

Cryptanalysis

No Spurious Local Minima in a Two Hidden Unit ReLU Network

2018-01-01 · ICLR 2018 1 · Chenwei Wu, Jiajun Luo, Jason D. Lee

Deep learning models can be efficiently optimized via stochastic gradient descent, but there is little theoretical evidence to support this. A key question in optimization is to understand when the optimization landscape…

Vocal Bursts Valence Prediction