3 papers
cs.CR2026
On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models
Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari
Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, a…
cs.CR2026
SATLOCK: Handover-Coupled Scheduling for Weather-Resilient Quantum Key Distribution over LEO Constellations
Mohammad Arif Hossain, Md Jafrin Hossain
Routing quantum keys over low-earth-orbit (LEO) satellite constellations is harder than classical routing: satellite handovers couple consecutive scheduling decisions, stochastic c…
cs.AI2026
The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu +1
Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, in…