Open AccessPosted Content
Automated Deepfake Detection
Reads0
Chats0
TLDR
In this article, a multi-task strategy was proposed to estimate potential manipulation regions in given samples as well as predict whether the samples are real or not. But, their method depends much less on prior knowledge, such as no need to know which manipulation method is utilized and whether it is utilized already.Abstract:
In this paper, we propose to utilize Automated Machine Learning to
automatically search architecture for deepfake detection. Unlike previous
works, our method benefits from the superior capability of deep learning while
relieving us from the high labor cost in the manual network design process. It
is experimentally proved that our proposed method not only outperforms previous
non-deep learning methods but achieves comparable or even better prediction
accuracy compared to previous deep learning methods. To improve the generality
of our method, especially when training data and testing data are manipulated
by different methods, we propose a multi-task strategy in our network learning
process, making it estimate potential manipulation regions in given samples as
well as predict whether the samples are real. Comparing to previous works using
similar strategies, our method depends much less on prior knowledge, such as no
need to know which manipulation method is utilized and whether it is utilized
already. Extensive experimental results on two benchmark datasets demonstrate
the effectiveness of our proposed method on deepfake detection.read more
References
More filters
Proceedings ArticleDOI
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
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.
Proceedings Article
Swapping Autoencoder for Deep Image Manipulation
TL;DR: The Swapping Autoencoder as mentioned in this paper uses two independent components to encode co-occurrent patch statistics across different parts of an image and enforce that any swapped combination maps to a realistic image.
Proceedings ArticleDOI
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
TL;DR: In this article, the authors demonstrate that it is possible to bypass deep neural networks by adversarially modifying fake videos synthesized using existing Deepfake generation methods, and further demonstrate that their adversarial perturbations are robust to image and video compression codecs.
Proceedings ArticleDOI
DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
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.
Posted Content
Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation.
TL;DR: A novel Adversarial Style Mining approach, which combines the style transfer module and task-specific module into an adversarial manner, which achieves state-of-the-art adaptation performance under the challenging one-shot setting.