Rishi D. Jha

speaking

invited

  1. All AI Models Might Be the Same: Harnessing the Universal Geometry of Embeddings

    Tufts University | Symposium on the Platonic Space | December 2025 | Remote

  2. Breaking and Fixing Multi-Agent Systems

    UC Berkeley | Security and AI Seminar | November 2025 | Berkeley, CA

  3. Contextual Control and Information Flow in Multi-Agent Systems

    Microsoft Applied Sciences | August 2025 | Redmond, WA

  4. Harnessing the Universal Geometry of Embeddings

    Planet Labs | July 2025 | Remote

  5. Multi-Agent Systems Execute Arbitrary Malicious Code

    Microsoft Research | Security and Privacy Workshop | July 2025 | Redmond, WA

  6. Multi-Agent Systems Execute Arbitrary Malicious Code

    MongoDB | May 2025 | New York, NY

  7. Emergent Risks in Multimodality

    Microsoft Applied Sciences | March 2025 | Remote

guest lectures

  1. Hacking AI Agents

    Cornell Tech | CS5434: Trustworthy AI | November 2025 | New York, NY

  2. Security & Privacy in Machine Learning

    Cornell Tech | CS5435: Security and Privacy Concepts in the Wild | April 2025 | New York, NY

  3. Topics on Sparse Coding

    The Overlake School | Neuroscience Club | April 2021 | Remote