paper-with-me

홈 › Papers

Adversarial Example Generation using Evolutionary Multi-objective Optimization

2019-12-30 · Takahiro Suzuki, Shingo Takeshita, Satoshi Ono

This paper proposes Evolutionary Multi-objective Optimization (EMO)-based Adversarial Example (AE) design method that performs under black-box setting. Previous gradient-based methods produce AEs by changing all pixels of a target image, while previous EC-based method changes small number of pixels to produce AEs. Thanks to EMO's property of population based-search, the proposed method produces various types of AEs involving ones locating between AEs generated by the previous two approaches, which helps to know the characteristics of a target model or to know unknown attack patterns. Experimental results showed the potential of the proposed method, e.g., it can generate robust AEs and, with the aid of DCT-based perturbation pattern generation, AEs for high resolution images.

📄 PDF Abstract BibTeX arXiv:2001.05844

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition

2020-12-21 · Shoma Ishida, Satoshi Ono

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the…

Adversarial AttackAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1

Generating Adversarial Examples with an Optimized Quality

2020-06-30 · Aminollah Khormali, DaeHun Nyang, David Mohaisen

Deep learning models are widely used in a range of application areas, such as computer vision, computer security, etc. However, deep learning models are vulnerable to Adversarial Examples (AEs),carefully crafted samples …

Adversarial AttackComputer Security

Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization

2018-11-04 · Shreya Khare, Rahul Aralikatte, Senthil Mani

Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either r…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

2021-01-19 · ICML Workshop AML 2021 7 · Jie Wang, Zhaoxia Yin, Jing Jiang, Yang Du

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial…

Adversarial Attack

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

2023-07-13 · Jialiang Sun, Wen Yao, Tingsong Jiang, Xiaoqian Chen

Deep neural networks have proven to be vulnerable to adversarial attacks in the form of adding specific perturbations on images to make wrong outputs. Designing stronger adversarial attack methods can help more reliably …

Adversarial AttackAutoML