Security of Facial Forensics Models Against Adversarial Attacks

@article{Huang2020SecurityOF,
  title={Security of Facial Forensics Models Against Adversarial Attacks},
  author={Rong Huang and Fuming Fang and Huy Hoang Nguyen and Junichi Yamagishi and Isao Echizen},
  journal={2020 IEEE International Conference on Image Processing (ICIP)},
  year={2020},
  pages={2236-2240}
}
Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether they are secure against adversarial attacks. We experimentally demonstrated the existence of individual adversarial perturbations (IAPs) and universal adversarial perturbations (UAPs) that can lead a well-performed FFM to misbehave. Based on iterative procedure, gradient information is used to generate two kinds of… Expand
1 Citations
Machine learning with digital forensics for attack classification in cloud network environment
  • Shaweta Sachdeva, Aleem Ali
  • Computer Science
  • International Journal of System Assurance Engineering and Management
  • 2021
In this paper, various Distributed Denial of service attacks like Internet Control Message Protocol Attack, Transmission Control Protocol Sync Attack, and User Datagram Protocol Attack wereExpand

References

SHOWING 1-10 OF 27 REFERENCES
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
TLDR
A forensic embedding based on a novel autoencoder-based architecture that can be used to distinguish between real and fake imagery is learned, which acts as a form of anomaly detector and shows significant improvements in transferability. Expand
Objective Perceptual Video Quality Measurement Techniques for Broadcasting Applications Using Low Definition Television in the Presence of a Full Reference Signal
  • 2010.
  • 2010
Objective Perceptual Video Quality Measurement Techniques for Broadcasting Applications Using Low Definition Television in the Presence of a Full Reference Signal
  • 2010.
  • 2010
Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos
TLDR
A convolutional neural network is designed that uses the multi-task learning approach to simultaneously detect manipulated images and videos and locate the manipulated regions for each query and fine-tuning using just a small amount of data enables the network to deal with unseen attacks. Expand
MesoNet: a Compact Facial Video Forgery Detection Network
TLDR
A method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Expand
Identification of deep network generated images using disparities in color components
TLDR
This paper proposes a feature set to capture color image statistics for identifying deep network generated (DNG) images and shows that the DNG images are more distinguishable from real ones in the chrominance components, especially in the residual domain. Expand
Adversarial Examples: Attacks and Defenses for Deep Learning
TLDR
The methods for generating adversarial examples for DNNs are summarized, a taxonomy of these methods is proposed, and three major challenges in adversarialExamples are discussed and the potential solutions are discussed. Expand
Exposing Deep Fakes Using Inconsistent Head Poses
  • X. Yang, Yuezun Li, Siwei Lyu
  • Computer Science
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
TLDR
This paper proposes a new method to expose AI-generated fake face images or videos based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images. Expand
Exposing DeepFake Videos By Detecting Face Warping Artifacts
TLDR
A new deep learning based method that can effectively distinguish AI-generated fake videos from real videos is described, which saves a plenty of time and resources in training data collection and is more robust compared to others. Expand
FaceForensics++: Learning to Detect Manipulated Facial Images
TLDR
This paper proposes an automated benchmark for facial manipulation detection, and shows that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers. Expand
...
1
2
3
...