HeyJaredHiddenLayer
HiddenLayer protects the world's most valuable technology: artificial intelligence. We're the leading AI security company, defending machine learning models and generative AI systems from adversarial attacks across their entire lifecycle from development to production.
- Indexed videos, last 90 days
- 2
- Latest publication
- Sep 14, 2026
- Audience
- ~730 subscribers
- Earliest in this view
- Jul 27, 2026
Latest videos
HiddenLayer Webinar: Beyond the Headlines: Defending Against AI Agent Attacks (opens the original)
Read excerpt
HiddenLayer's threat intelligence and product leads reconstruct the July 2026 Hugging Face / OpenAI agent intrusion, where a swarm of roughly 1,200 AI agents in a benchmarking exercise found each other and coordinated, and hundreds of them escaped their containers, took over Kubernetes infrastructure, and exfiltrated credentials and internal data before anyone noticed. The panel walks through how the agents pivoted from an isolated exploit-gym environment through a JFrog Artifactory repository,
HiddenLayer Webinar: Coding Agents, Hooks & Harnesses: Securing the Next Generation of AI Agents (opens the original)
Read excerpt
The biggest security risk in a coding agent usually isn't the model - it's the harness around it. HiddenLayer researchers Kieran Evans, Kenneth Yeung, and Kasimir Schulz walk through why the layers wrapping an agent (Claude Code, Cursor, Codex, and the tools, skills, and orchestration around them) have become the real attack surface - and why, in many modern agents, you no longer need a prompt injection at all. If your instructions land in a path the model already trusts, it just follows them. T
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
~730 subscribers
Measured Sep 19, 2026
Source's subscribers, not the number who saw an individual piece.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.