works on

From the 2 of 9 linked papers with an AI index.

collaborators

9 papers

cs.CR2026

Open-Source Intelligence for Code Provenance and the Security Patterns that Separate Human and Large-Language-Model Implementations of Common Programming Tasks

Mohammadreza Rashidi

The paper builds a reproducible pipeline to determine whether code snippets come from humans or large language models and compares the security patterns each source uses for common…

cs.CR2026

Open-Source Intelligence and Music Information Retrieval for Geographic Attribution of Musical Affect and the Ecological Limits of Population Inference

Mohammadreza Rashidi

The study extracts melodic and affective features from thousands of folk melodies across 16 countries, finds strong geographic differences in musical structure, but shows that thes…

cs.CR2026

Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

Mohammadreza Rashidi

The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/list handshake that returns a n…

cs.CR2026

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

Mohammadreza Rashidi

AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer aro…

cs.CV2026

Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection

Mohammadreza Rashidi

Automated "suspicious behavior" flagging is a headline promise of AI surveillance, and the field reports high frame-level ROC-AUC on standard video anomaly detection benchmarks. Th…

cs.CV2026

Empirical Evaluation of Multi-Modal Touch Detection in Over-the-Shoulder Video Surveillance

Mohammadreza Rashidi

Video Intelligence Surveillance (VIDINT) on over-the-shoulder footage is a proposed vector for monitoring human-computer interaction patterns without direct screen recording access…