Publications
A. Sarkar, A. DiChristofano, S. Das, P. J Fowler, N. Jacobs, Y. Vorobeychik
Accepted at Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems
(AAMAS 2024).
Y. Xu, M. Lanier, A. Sarkar, Y. Vorobeychik
Accepted at AAAI Workshop on "AI for Cyber Security" (AAAI 2024).
How Powerful are K-hop Message Passing Graph Neural Networks.
J. Feng, Y. Chen, F. li, A. Sarkar, M. Zhang
Accepted at 36th Conference on Neural Information Processing Systems
(NeurIPS 2022).
Empowering a Robust Model with Stable and Object-Aligned Explanations.
S. Gali, A. Sarkar & V. Balasubramanian
Accepted at European Conference on Computer Vision (ECCV 2022) Workshop on "Adversarial Robustness In The Real World".
Please click here for more details.
Leveraging Test-Time Consensus Prediction for Robustness against Unseen Noise.
A. Sarkar, A. Sarkar, V. N Balasubramanian,
Accepted at IEEE-CVF Winter Conference on Applications of Computer Vision (WACV 2022).
Also Accepted at the International Conference on Computer Vision (ICCV 2021) Workshop on "Adversarial Robustness In The Real World " .
Please click here for more details.
Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach.
A.Sarkar, A.Sarkar, S. Gali & V. Balasubramanian
Accepted at the 35th Conference on Neural Information Processing Systems
(NeurIPS 2021).
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation.
A. Sarkar, R. Iyengar.
Accepted at 29th International Conference on Artificial Neural Network
(ICANN 2020)
Please click here for more details.
Inducing Semantic Grouping of Latent Concepts for Explanations: An Ante-Hoc Approach.
A. Sarkar, D. Vijaykeerthy, A. Sarkar, V. Balasubramanian.
Arxiv/ Preprint Paper.
Please click here for more details.
ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness.
A. Sarkar, A. Raj, R. Iyengar
Accepted at the 19th International Conference on Machine Learning and Applications
(IEEE ICMLA 2020)
Please click here for more details.
Curated model development using NEUROiD: A web-based NEUROmotor integration and Design platform.
Acknowledged for the initial literature study and laying the foundations on which NEUROiD was built.
Accepted at
(Frontiers in Neuroinformatics 2019).
Please click here for more details.