1 citations · 1 across the 1 of their papers we have counts for
3 papers
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Sarim Hashmi, Mukul Ranjan, Kshitij Mishra +3
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The…
On the Effectiveness of Kernel-Level Evidence for Agent Security
Spencer King, Zhilu Zhang, Mikhail Kuznetsov +3
LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the application…
Efficient Hierarchical Transformers for Representing Log Data
Zhichao Hou, Mina Ghashami, Mikhail Kuznetsov +3
Transformers have gained widespread acclaim for their versatility in handling diverse data structures, yet their application to log data remains underexplored. Log data, characteri…