dc.contributor.author | Goel, Akhil | |
dc.contributor.author | Singh, Anirudh | |
dc.contributor.author | Vatsa, Mayank (Advisor) | |
dc.contributor.author | Singh, Richa (Advisor) | |
dc.date.accessioned | 2019-10-09T07:40:10Z | |
dc.date.available | 2019-10-09T07:40:10Z | |
dc.date.issued | 2019-04-30 | |
dc.identifier.uri | http://repository.iiitd.edu.in/xmlui/handle/123456789/777 | |
dc.description.abstract | Extensive research on attacks on deep learning models has shown that these models are not as robust as they seem. A carefully designed low magnitude perturbation is enough to cause havoc and completely confuse the model. This project addresses this pitfall by first developing a benchmarking adversarial detection and adversary mitigation toolbox for face recognition, then by proposing a defense technique that alleviates the embedded imperceptible noise and nally by proposing a blockchain-based architecture for the deep learning models. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | IIITD-Delhi | en_US |
dc.subject | Adversarial Attacks | en_US |
dc.subject | Adversarial Mitigation | en_US |
dc.subject | Adversarial Detection | en_US |
dc.subject | Deep Learning | en_US |
dc.subject | Security | en_US |
dc.title | Adversary detection tool | en_US |
dc.type | Other | en_US |