Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
Labiad, Ismail, Bäck, Thomas, Fernandez, Pierre, Najman, Laurent, Sander, Tom, Ye, Furong, Zameshina, Mariia, Teytaud, Olivier
–arXiv.org Artificial Intelligence
In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial attacks. However, these attacks are easily detected due to their specific initial distribution. We therefore consider other black-box attacks, inspired from generic black-box optimization tools, and in particular the log-normal algorithm. We apply the log-normal method to the attack of fake detectors, and get successful attacks: importantly, these attacks are not detected by detectors specialized on classical adversarial attacks. Then, combining these attacks and deep detection, we create improved fake detectors.
arXiv.org Artificial Intelligence
Sep-25-2024
- Country:
- Europe (0.68)
- North America > United States
- Massachusetts (0.14)
- Genre:
- Research Report (0.82)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Evolutionary Systems (1.00)
- Neural Networks (1.00)
- Performance Analysis > Accuracy (0.47)
- Statistical Learning (0.93)
- Representation & Reasoning > Optimization (1.00)
- Vision (0.93)
- Machine Learning
- Security & Privacy (1.00)
- Sensing and Signal Processing > Image Processing (1.00)
- Artificial Intelligence
- Information Technology