OMAR, LUMA,QASSAM,ABEDALQADER (2018) Face Liveness Detection under Processed Image Attacks. Doctoral thesis, Durham University.
Face recognition is a mature and reliable technology for identifying people. Due
to high-deﬁnition cameras and supporting devices, it is considered the fastest and
the least intrusive biometric recognition modality. Nevertheless, eﬀective spooﬁng
attempts on face recognition systems were found to be possible. As a result, various anti-spooﬁng algorithms were developed to counteract these attacks. They are
commonly referred in the literature a liveness detection tests. In this research we highlight the eﬀectiveness of some simple, direct spooﬁng attacks, and test one of
the current robust liveness detection algorithms, i.e. the logistic regression based face liveness detection from a single image, proposed by the Tan et al. in 2010, against malicious attacks using processed imposter images. In particular, we study experimentally the eﬀect of common image processing operations such as sharpening and smoothing, as well as corruption with salt and pepper noise, on the face liveness detection algorithm, and we ﬁnd that it is especially vulnerable against spooﬁng attempts using processed imposter images. We design and present a new facial database, the Durham Face Database, which is the ﬁrst, to the best of our knowledge, to have client, imposter as well as processed imposter images. Finally, we evaluate our claim on the eﬀectiveness of proposed imposter image attacks using transfer learning on Convolutional Neural Networks. We verify that such attacks are more diﬃcult to detect even when using high-end, expensive machine learning techniques.
|Item Type:||Thesis (Doctoral)|
|Award:||Doctor of Philosophy|
|Faculty and Department:||Faculty of Science > Computer Science, Department of|
|Copyright:||Copyright of this thesis is held by the author|
|Deposited On:||05 Oct 2018 11:23|