paper-with-me

홈 › Papers

Towards Deep Neural Network Architectures Robust to Adversarial Examples

2014-12-11 · Shixiang Gu, Luca Rigazio

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are often imperceptible, but can result in 100% mis-classification for a state of the art DNN. We study the structure of adversarial examples and explore network topology, pre-processing and training strategies to improve the robustness of DNNs. We perform various experiments to assess the removability of adversarial examples by corrupting with additional noise and pre-processing with denoising autoencoders (DAEs). We find that DAEs can remove substantial amounts of the adversarial noise. How- ever, when stacking the DAE with the original DNN, the resulting network can again be attacked by new adversarial examples with even smaller distortion. As a solution, we propose Deep Contractive Network, a model with a new end-to-end training procedure that includes a smoothness penalty inspired by the contractive autoencoder (CAE). This increases the network robustness to adversarial examples, without a significant performance penalty.

📄 PDF Abstract BibTeX arXiv:1412.5068

Code (2)

aaronmckinstry706/toward-robust-dnn tf
ypotdevin/randomized-defenses

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Contractive Autoencoder A Contractive Autoencoder is an autoencoder that adds a penalty term to the classical reconstruction cost function. This penalty term corresponds to the Frobenius norm of the…
Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks

2021-06-03 · NeurIPS 2021 12 · Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon

Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architec…

Enhance transferability of adversarial examples with model architecture

2022-02-28 · Mingyuan Fan, Wenzhong Guo, Shengxing Yu, Zuobin Ying 외

Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but …

model

Common Knowledge Learning for Generating Transferable Adversarial Examples

2023-07-01 · Ruijie Yang, Yuanfang Guo, Junfu Wang, Jiantao Zhou 외

This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples by a substitute (source) model and utilize them to attack an unse…

Delving into adversarial attacks on deep policies

2017-05-18 · Jernej Kos, Dawn Song

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. …

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Mischief: A Simple Black-Box Attack Against Transformer Architectures

2020-10-16 · Adrian de Wynter

We introduce Mischief, a simple and lightweight method to produce a class of human-readable, realistic adversarial examples for language models. We perform exhaustive experimentations of our algorithm on four transformer…