Avatar

Nicholas Conley

AI Defense Researcher

AI Software & Platform

Nicholas J. Conley is an AI Researcher on the Threat Intelligence team for Cisco AI Defense, specializing in emerging AI security threats, AI red teaming, and defenses for LLMs and agentic systems. Prior to Cisco, he served as Vice President - Lead AI Cybersecurity Engineer at JPMorgan Chase and Co., where he established the AI Red Teaming Service—including tooling and supporting infrastructure—developed tools for AI model security inference testing, created an enterprise AI Attack Library, and conducted gap assessments against MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLMs, and the EU AI Act. Prior to JPMC, Nicholas held a role at KPMG, where he delivered cyber defense and cloud solutions for Fortune 100 clients. Nicholas holds a B.S. in Cybersecurity Analytics and Operations from The Pennsylvania State University.

Articles

How safe are gpt-oss-safeguard models?

5 min read

Large language models (LLMs) have become essential tools for organizations, with open weight models providing additional control and flexibility for customizing models to their specific use cases. Last year, OpenAI released its gpt-oss series, including standard and, shortly after, safeguard variants, focused on safety classification tasks. We decided to evaluate their raw security posture against […]

Death by a Thousand Prompts: Open Model Vulnerability Analysis

6 min read

AI models have become increasingly democratized, and the proliferation and adoption of open weight models has contributed significantly to this reality. Open-weight models provide researchers, developers, and AI enthusiasts with a solid foundation for limitless use cases and applications.  As of August 2025, leading U.S., Chinese, and European models have around 400M total downloads on […]