Xiaofei Xie

TL;DR: An automated fuzz testing framework for hunting potential defects of general-purpose DNNs, which performs metamorphic mutation to generate new semantically preserved tests, and leverages multiple plugable coverage criteria as feedback to guide the test generation from different perspectives.

TL;DR: This work proposes a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AI-synthesized fake faces, conjecture that monitoring neuron behavior can also serve as an asset in detecting fake faces since layer-by-layer neuron activation patterns may capture more subtle features that are important for the fake detector.

TL;DR: MobiTive as mentioned in this paper leverages customized deep neural networks to provide a real-time and responsive detection environment on mobile devices, which is a preinstalled solution rather than an app scanning and monitoring engine using after installation.

TL;DR: In this article, the authors introduce two novel adversarial attack techniques to stealthily and efficiently attack the DRL agents, which enable an adversary to inject adversarial samples in a minimal set of critical moments while causing the most severe damage to the agent.

TL;DR: A factor-aware rain generation that simulates rain steaks according to the camera exposure process and models the learnable rain factors for adversarial attack and the adversarial rain attack against the image classification and object detection is proposed.