3 citations · 3 across the 3 of their papers we have counts for
4 papers
SilentCall: Hidden Tool-Call Backdoors in Open-Weight Agents, and How to Catch Them
Bhanu Pallakonda, Mikkel Hindsbo, Sina Ehsani +1
Open-weight tool-calling agents are adopted on evidence of merit, usually benchmark scores and a record of reliable use. We show that a model publisher can train an agent that earn…
Mapping the Storm: Geospatial Impacts of Severe Weather on LEO Network Performance
Sina Ehsani, Bhanu Pallakonda, Pragyana K. Mishra
LEO satellite constellations, led by deployments such as Starlink, are playing an increasingly pivotal role in enabling global broadband connectivity. However, the reliability and…
Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs
Bhanu Pallakonda, Mikkel Hindsbo, Sina Ehsani +1
The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond lea…
Camera Control at the Edge with Language Models for Scene Understanding
Alexiy Buynitsky, Sina Ehsani, Bhanu Pallakonda +1
In this paper, we present Optimized Prompt-based Unified System (OPUS), a framework that utilizes a Large Language Model (LLM) to control Pan-Tilt-Zoom (PTZ) cameras, providing con…