CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network
arXiv:1811.01225v1
Originality Incremental advance
AI Analysis
This work addresses security vulnerabilities in machine learning models for applications requiring robust defenses against adversarial attacks, but it is incremental as it improves an existing method.
The paper tackled the problem of generating adversarial examples to fool both white-box and black-box models, achieving state-of-the-art performance and winning second place in the non-target task at CAAD 2018.
In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a state of the art performance and won the 2rd place in the non-target task in CAAD 2018.