Xiaofei Xie

TL;DR: DeepRhythm as discussed by the authors uses dual-spatial-temporal attention to adapt to dynamically changing face and fake types to detect DeepFakes by monitoring the heartbeat rhythms of real faces.

TL;DR: A mutation testing-based tool for DNNs, DeepMutation++, which facilitates the DNN quality evaluation, supporting both feed-forward neural networks (FNNs) and stateful recurrent neural Networks (RNNs), and allows to identify the vulnerable segments of a sequential input by runtime analysis.

TL;DR: Audee as discussed by the authors adopts a search-based approach and implements three different mutation strategies to generate diverse test cases by exploring combinations of model structures, parameters, weights and inputs, which is able to detect three types of bugs: logical bugs, crashes and Not-a-Number (NaN) errors.

TL;DR: In this article, the spatial-temporal sparse incremental perturbations are used to make the adversarial attack less perceptible. But, the work in this paper is different from previous work.

TL;DR: This work proposes a novel approach, named DeepSonar, based on monitoring neuron behaviors of speaker recognition system, i.e., a deep neural network (DNN), to discern AI-synthesized fake voices, and poses a new insight into adopting neuron behaviors for effective and robust AI aided multimedia fakes forensics as an inside-out approach.