PPL
Cristina Nita-Rotaru
Papers (4)
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMsAPWA: A Distributed Architecture for Parallelizable Agentic WorkflowsAttacks and Mitigations for Distributed Governance of Agentic AI under Byzantine AdversariesMAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security