Defense against Adversarial Examples by Encoder-Assisted Search in the Latent Coding Space
Deep neural networks were shown to be vulnerable to crafted adversarial perturbations, and thus bring serious safety problems. To solve this problem, we proposed $\text{AE-GAN}_\text{+sr}$, a framework for purifying input images by searching a closest natural reconstruction with little computation. We first build a reconstruction network AE-GAN, which adapted auto-encoder by introducing adversarial loss to the objective function. In this way, we can enhance the generative ability of decoder and preserve the abstraction ability of encoder to form a self-organized latent space. In the inference time, when given an input, we will start a search process in the latent space which aims to find the closest reconstruction to the given image on the distribution of normal data. The encoder can provide a good start point for the searching process, which saves much computation cost. Experiments show that our method is robust against various attacks and can reach comparable even better performance to similar methods with much fewer computations.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderSimilar Papers 제목 키워드 기반
Autoencoder-based Denoising Defense against Adversarial Attacks on Object Detection
Deep learning-based object detection models play a critical role in real-world applications such as autonomous driving and security surveillance systems, yet they remain vulnerable to adversarial examples. In this work, …
Autonomous DrivingObject DetectionPuVAE: A Variational Autoencoder to Purify Adversarial Examples
Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed…
Adversarial DefenseAdversarial Defense against FGSM AttackDISCO: Adversarial Defense with Local Implicit Functions
The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered. Inspired by the hypothesis that these examples lie beyond the natural…
Adversarial Defenseimage-classificationImage ClassificationCode-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' comput…
Denoisingimage-classificationImage ClassificationMagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.