Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models

2023-07-26 · Ryota Iijima, Miki Tanaka, Sayaka Shiota, Hitoshi Kiya

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption. In this article, we propose a random ensemble of encrypted ViT models to achieve much more robust models. In experiments, the proposed scheme is verified to be more robust against not only black-box attacks but also white-box ones than convention methods.

📄 PDF Abstract BibTeX arXiv:2307.13985

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

Randomized Adversarial Training via Taylor Expansion

2023-03-19 · CVPR 2023 1 · Gaojie Jin, Xinping Yi, Dengyu Wu, Ronghui Mu 외

In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the most successful methods. To deal with bot…

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

2024-07-16 · Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu 외

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized…

Adversarial Robustness

MagNet: a Two-Pronged Defense against Adversarial Examples

2017-05-25 · Dongyu Meng, Hao Chen

Deep learning has shown promising results on hard perceptual problems in recent years. However, deep learning systems are found to be vulnerable to small adversarial perturbations that are nearly imperceptible to human. …

Deep Learning Vocal Bursts Valence Prediction

Defense Against the Dark Arts: An overview of adversarial example security research and future research directions

2018-06-11 · Ian Goodfellow

This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and pro…

Deep Learning