IEEE

Seminar: Role and Strengths of Adversarial Perturbations in DL

 

Department of Computational and Data Sciences and IEEE SP Bangalore Chapter invite you for the following seminar

SPEAKER  : Dr. Mayank Vatsa and Dr. Richa Singh
TITLE         : Role and Strengths of Adversarial Perturbations in Deep Learning
Date/Time   : February 21, 2019 (Thursday) 11:00 AM
Venue          : 102 CDS Seminar Hall.


ABSTRACT

Deep neural network architecture based models have high expressive power and learning ca-pacity. Due to several advancements, deep learning based models have shown very high accuracies on challenging databases including face databases. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of repre-sentation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities.

Adversarial attacks on automated classification systems has been an area of interest for a long time. In 2002, Ratha et al. proposed eleven points of attacks on a biometric/face recognition system. For in-stance, an adversary can operate at the input/image level or the decision level, and lead to incorrect face recognition results. The research on adversarial learning for attacking face recognition systems has three key components: (i) creating adversarial images, (ii) detecting whether an image is adversely altered or not, and (iii) mitigating the effect of the adversarial perturbation process. These adversaries create dif-ferent kinds of effect on the input and detecting them requires the application of a combination of hand-crafted as well as learnt features; for instance, some of the existing attacks can be detected using prin-cipal components while some hand-crafted attacks can be detected using well defined image processing operations. Therefore, it is important to detect the adversarial perturbations and mitigate the effect caused due to such adversaries using ensemble of defense algorithms. While majority of the research in adversarial perturbations focus on attacking deep learning models, in this talk, we will also connect how adversarial perturbations can be used for building Trusted-AI systems. With two threads on this direc-tion, we will discuss privacy preserving applications in faces as well as a novel concept of Data Fine-tuning.

BIOGRAPHY

Mayank Vatsa received the M.S. and Ph.D. degrees in computer science from West Virginia University, USA, in 2005 and 2008, respectively. He is currently the Head of the Infosys Center for Artificial Intelli-gence, an Associate Professor with the IIIT-Delhi, India, and an Adjunct Associate Professor with West Virginia University, USA. He has co-edited a book Deep learning in Biometrics and co-authored over 250 research papers. His areas of interest are biometrics, image processing, machine learning, computer vi-sion, and information fusion. He is a Senior Member of IEEE and ACM. He was a recipient of A. R. Krish-naswamy Faculty Research Fellowship at the IIIT-Delhi, the FAST Award Project by DST, India, and several Best Paper and Best Poster Awards at international conferences. He is also the recipient of the prestigious Swarnajayanti fellowship award from Government of India. He is an Area Chair of the Information Fusion (Elsevier), General Co-Chair of IJCB 2020, and the PC Co-Chair of the ICB 2013 and IJCB 2014. He has served as the Vice President (Publications) of the IEEE Biometrics Council where he started the IEEE Transactions on Biometrics, Behavior, And Identity Science.

 

Richa Singh received the Ph.D. degree in computer science from West Virginia University, Morgantown, USA, in 2008. She  is  currently an  Associate Dean of  Alumni and  Communications,  an Associate Professor with the IIIT-Delhi, India, and an Adjunct Associate Professor with West Virginia University. She has co-edited book Deep Learning in Biometrics and has delivered tutorials on deep learning and domain adap-tation in ICCV 2017, AFGR 2017, and IJCNN 2017. Her areas of interest are pattern recognition, machine learning, and biometrics. She is a fellow of IAPR and a Senior Member of IEEE and ACM. She was a recipient of the Kusum and Mohandas Pai Faculty Research Fellowship at the IIIT-Delhi, the FAST Award by the Department of Science and Technology, India, and several best paper and best poster awards in interna-tional conferences. She has also served as the Program Co-Chair of BTAS 2016 and IWBF 2018, and a General Co-Chair of ISBA 2017. She is currently serving as a Program Co-Chair of AFGR 2019 and IJCB 2020. She is serving as the Vice President (Publications) of the IEEE Biometrics Council. She is an Editorial Board Member of Information Fusion (Elsevier), an Associate Editor of Pattern Recognition, Computer Vision and Image Understanding, and the EURASIP Journal on Image and Video Processing (Springer).

____________
ALL ARE WELCOME

Leave a Reply