Ezekiel Soremekun
2 papers · Latest:
Cryptography & Security
Malicious ML Model Detection by Learning Dynamic Behaviors
DynaHug detects malicious pre-trained ML models by learning benign models' dynamic runtime behaviors, outperforming static analysis.
2604.19438
Software EngineeringMUCOCO: Automated Consistency Testing of Code LLMs
MUCOCO introduces an automated method using semantic-preserving mutation to test and expose inconsistent behaviors in Code LLMs, outperforming baselines.
2604.19086
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.