Ensuring Resilience and Efficiency in Distributed AI Systems

#Distributed #AI #Federated #Learning #Edge #Physical #Internet #of #Things #(IoT) #On-Device #Intelligence #Resource-Efficient #Continual #Hyperdimensional #Computing #Adversarial #Robustness #Security #Data #Privacy #Multi-Agent #Systems #Trustworthy #OpenFL #MART #LLMart #ATLAS.

The shift toward physical AI, IoT and on-device agents, combined with privacy, latency and
bandwidth constraints, is driving the need for distributed intelligence at the edge. Distributed AI
unlocks siloed data and enables collaborative learning across devices while keeping data local.
However, it faces challenges from limited and heterogeneous edge resources (data, computation
and connectivity), the need to learn continually from streaming data, and new security and privacy
threats. This talk gives an overview of our research on making distributed and federated AI both
efficient and trustworthy, spanning resource-efficient and continual federated learning,
hyperdimensional computing, and adversarial robustness and privacy. It also highlights our open-
source tools: OpenFL, MART, LLMart and ATLAS. The talk closes with future directions for securing
emerging multi-agent and distributed AI systems.

• Add Event to Calendar
  iCal
  Google Calendar

• Santa Clara University
• 500 El Camino Real
• Santa Clara, California
• United States 95053
• Building: Sobrato Campus for Discovery and Innovation (SCDI)
• Room Number: 4010

---

• Contact Event Host
• Co-sponsored by Santa Clara University

• Starts 28 October 2026 07:00 AM UTC
• Ends 03 November 2026 01:00 AM UTC
• No Admission Charge

•