AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Christian Liebel · September 17, 2026

Browser AI: check model availability and make cloud fallbacks explicit

guide AI EngineeringAgent Security
Why it matters

Christian Liebel’s September slides compare browser-managed AI APIs, applications that supply their own models, and emerging ways to expose website tools to agents. The examples make deployment constraints visible: browser support, model downloads, initialization, device resources, and the choice of local or remote inference. Chrome’s companion polyfill documentation confirms that a familiar browser API can use a cloud backend, changing where prompts are processed. The practical lesson is to test capability and data flow rather than infer privacy from an API name. Experimental browser tooling requires feature detection and compatibility checks on the devices being supported.

My takeaway: Test supported, unsupported, first-download, and offline states. Inspect network traffic for each configured backend, disclose remote processing before sending sensitive input, and keep provider secrets out of browser-delivered code.
Keep exploring

More curated notes connected through AI Engineering and Agent Security.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

Microsoft Security Blog · guide

AI vulnerability research: measure reproducible findings and completed fixes

Microsoft’s FORGE account describes the work between a model’s vulnerability claim and a useful repair: reusable builds, duplicate removal, reachability checks, project-specific verification, reproducible triggers and regression tests. Structured rejection reasons help improve later searches. The useful operational measure is the flow of findings that survive verification and reach a fix, rather than the number of candidates generated. Reported successful-case costs exclude parts of screening, failed attempts and human work, so they are not the total cost of operating this pipeline.

OpenAI News · framework

Frontier training safety cases: connect evidence to enforced pause and rollback controls

OpenAI proposes training-run safety cases combining alignment evaluations, containment and monitoring with explicit operational ownership. Concrete measures include immutable transcripts, held-out incident tests, checks for evaluation gaming, response deadlines and fail-closed monitoring. Independent internal challenge, leadership vetoes and tracking downstream uses support stopping a run and reversing affected work. The article describes recommendations still being implemented, rather than audited proof that every safeguard already operates or that residual risk has been eliminated.