4 papers
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol (MCP) Layers
Nahom Birhan, Mehrdad Rostamzadeh, Sidhant Narula +3
Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool schemas, tool out…
SIDE: Sensor Impersonation Detection at the Edge via Sequence Prediction
Nahom Birhan
Some low-cost Internet of Things (IoT) sensor deployments lack device-level source authentication, leaving them vulnerable to impersonation or injected sensor readings. We present…
MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security
Mehrdad Rostamzadeh, Sidhant Narula, Nahom Birhan +2
The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introdu…
DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning
Nahom Birhan, Daniel Wesego, Dereje Shenkut +2
Personalized federated learning (PFL) creates client-specific models to handle data heterogeneity. Previously, PFL has been shown to be naturally resistant to backdoor attack propa…