Publications

APWA: A Distributed Architecture for Parallelizable Agentic Workflows

arXiv preprint · May 2026

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries

arXiv preprint · May 2026

MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security

arXiv preprint · May 2026

Retrieval-Augmented LLMs for Security Incident Analysis

ACM CAIS 2026

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

arXiv preprint · February 2026

Beware Untrusted Simulators: Reward-Free Backdoor Attacks in Reinforcement Learning

ICLR 2026

SAGA: A Security Architecture for Governing AI Agentic Systems

arXiv preprint · April 2025

ACE: A Security Architecture for LLM-Integrated App Systems

NDSS 2026

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

NeurIPS 2024

Adversarial Inception Backdoor Attacks against Reinforcement Learning

ICML 2025