University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Is it even possible to defend AI agents against attacks in practice?

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Is it even possible to defend AI agents against attacks in practice?

Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik .

NOTE unusual place (FW11)

Prompt injections make deployment of AI agents hard in practice. In this talk I will cover the current status quo in agentic AI security and try predicting where the future will take us.

Bio: Ilia Shumailov holds a PhD in Computer Science from the University of Cambridge. Until recently Ilia was a Senior Research Scientist at Google DeepMind focusing on the intersection of machine learning, privacy, and computer security. At present Ilia runs a company sequrity.ai building tools to secure AI agents of the future.

You can also join us on Zoom

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Latimer Room, Old Court Clare College, Trinity Lane, Cambridge CB2 1TL Friends Meeting House, 12 Jesus Lane English Faculty, GR06/07

Other talks

Bigger Picture Talk: Developing future marine engines running on ammonia and other green fuels title abstract tba CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models Tea and Coffee Break Morning Tea and Coffee TBC
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity