Uploaded January 2022 | Updated September 2026, 1 hour ago
ArtIAMAS Seminar Series: Building Resilience against Cyberattacks
Aryya Gangopadhyay
Professor
Information Systems department
University of Maryland, Baltimore County
In this talk we will address the issue of building resilient systems in the face of cyberattacks. We will present defense mechanism for cyberattacks using a 3-tier architecture that can be used to secure army assets and tactical information. The top tier represents the front-end where autonomous sensing and inferencing through AI models take place by UAVs, UGVs, etc. We will illustrate how models can be defended against data poisoning attacks. In the middle tier we focus on building cyber defense against attacks in federated learning environments, where models are trained on large corpus of decentralized data without transferring raw over a communication channel. The bottom tier represents back-end servers that train deep learning models with large amounts of data that can subsequently be pushed to the edge for inferencing. We will demonstrate how adaptive models can be developed for detecting and preventing various types of attacks at this level.
For more information on the Maryland Robotics Center see:
https://robotics.umd.edu
ArtIAMAS Seminar Series: Building Resilience against Cyberattacks
Aryya Gangopadhyay
Professor
Information Systems department
University of Maryland, Baltimore County
In this talk we will address the issue of building resilient systems in the face of cyberattacks. We will present defense mechanism for cyberattacks using a 3-tier architecture that can be used to secure army assets and tactical information. The top tier represents the front-end where autonomous sensing and inferencing through AI models take place by UAVs, UGVs, etc. We will illustrate how models can be defended against data poisoning attacks. In the middle tier we focus on building cyber defense against attacks in federated learning environments, where models are trained on large corpus of decentralized data without transferring raw over a communication channel. The bottom tier represents back-end servers that train deep learning models with large amounts of data that can subsequently be pushed to the edge for inferencing. We will demonstrate how adaptive models can be developed for detecting and preventing various types of attacks at this level.
For more information on the Maryland Robotics Center see:
https://robotics.umd.edu
