paper-with-me

Papers

Block Switching: A Stochastic Approach for Deep Learning Security

2020-02-18 · Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions, while maintain imperceptible to human vision system. In this paper, we introduce Block Switching (BS), a defense strategy against adversarial attacks based on stochasticity. BS replaces a block of model layers with multiple parallel channels, and the active channel is randomly assigned in the run time hence unpredictable to the adversary. We show empirically that BS leads to a more dispersed input gradient distribution and superior defense effectiveness compared with other stochastic defenses such as stochastic activation pruning (SAP). Compared to other defenses, BS is also characterized by the following features: (i) BS causes less test accuracy drop; (ii) BS is attack-independent and (iii) BS is compatible with other defenses and can be used jointly with others.

📄 PDF Abstract BibTeX arXiv:2002.07920

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Test 설명 없음

Similar Papers 제목 키워드 기반

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

2022-03-11 · Anirudh Yadav, Ashutosh Upadhyay, S. Sharanya

According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns …

Adversarial AttackBIG-bench Machine LearningSelf-Driving Cars

Exact and Evolutionary Algorithms for Sequential Multi-Objective Transmission Topology Planning

2026-05-05 · Job Groeneveld, Miguel Muñoz, Jan Viebahn, Alessandro Zocca arxiv

We study day-ahead transmission topology control for high-voltage grid operation under $N-1$ security constraints. The operational task is to select, over a 24-hour horizon, a sequence of substation topologies obtained v…

Decision Making

Spectral clustering in the dynamic stochastic block model

2017-05-02 · Marianna Pensky, Teng Zhang

In the present paper, we studied a Dynamic Stochastic Block Model (DSBM) under the assumptions that the connection probabilities, as functions of time, are smooth and that at most $s$ nodes can switch their class members…

ClusteringmodelStochastic Block Model

Alternative models for FX: pricing double barrier options in regime-switching Lévy models with memory

2024-02-26 · Svetlana Boyarchenko, Sergei Levendorskiĭ

This paper is a supplement to our recent paper ``Alternative models for FX, arbitrage opportunities and efficient pricing of double barrier options in L\'evy models". We introduce the class of regime-switching L\'evy mod…

Stabilization of Microbial Communities by Responsive Phenotypic Switching

2021-12-12 · Pierre A. Haas, Maria A. Gutierrez, Nuno M. Oliveira, Raymond E. Goldstein

Clonal microbes can switch between different phenotypes and recent theoretical work has shown that stochastic switching between these subpopulations can stabilize microbial communities. This phenotypic switching need not…