activity
20232025
most citedA Closer Look at the Limitations of Instruction Tuning

3 citations · 6 across the 12 of their papers we have counts for

collaborators
Showing cs.CRShow all

2 papers · 1 filter

cs.CR2025

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Léo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru +7

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the a…

cs.CR2025

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats

Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…