Advancing the Science of AI Security

The HiddenLayer AI Security Research team uncovers vulnerabilities, develops defenses, and shapes global standards to ensure AI remains secure, trustworthy, and resilient.

Turning Discovery Into Defense

Our mission is to identify and neutralize emerging AI threats before they impact the world. The HiddenLayer AI Security Research team investigates adversarial techniques, supply chain compromises, and agentic AI risks, transforming findings into actionable security advancements that power the HiddenLayer AI Security Platform and inform global policy.

Meet the Experts Defining AI Security

Our AI Security Research Team

HiddenLayer’s research team combines offensive security experience, academic rigor, and a deep understanding of machine learning systems.

Kenneth Yeung

Senior AI Security Researcher

Conor McCauley

Adversarial Machine Learning Researcher

Jim Simpson

Principal Intel Analyst

Jason Martin

Director, Adversarial Research

Andrew Davis

Chief Data Scientist

Marta Janus

Principal Security Researcher

Eoin Wickens

Director of Threat Intelligence

Kieran Evans

Principal Security Researcher

Ryan Tracey

Principal Security Researcher

Kasimir Schulz

Director, Security Research

Our Impact by the Numbers

Quantifying the reach and influence of HiddenLayer’s AI Security Research.

75
%
+

Reduction in exposure to AI exploits

50
+
𝘊𝘝𝘌𝘴

Disclosed through our security research

30
+

Issued patents

In the News

HiddenLayer’s research is shaping global conversations about AI security and trust.

IN THE NEWS
XX
min read
HiddenLayer Selected to Support DOE’s $60 Million Prometheus Initiative Under the Genesis Mission

HiddenLayer joins the DOE’s $60M Prometheus initiative to help secure AI applications across the U.S. nuclear energy sector and critical infrastructure.

IN THE NEWS
XX
min read
HiddenLayer Appoints Mike Gesnaldo as Chief Revenue Officer to Accelerate Next Phase of Growth

HiddenLayer appoints Mike Gesnaldo as Chief Revenue Officer to scale its go-to-market organization and help enterprises securely adopt AI.

IN THE NEWS
XX
min read
HiddenLayer Unveils Agent Harness Security to Protect AI-Powered Software Development at Runtime

HiddenLayer announces Agent Harness Security, a runtime security solution that protects AI coding agents from prompt injection, secret exposure, unsafe commands, and other runtime threats while preserving developer productivity.

Get all our Latest Research & Insights

Explore our glossary to get clear, practical definitions of the terms shaping AI security, governance, and risk management.