NDC Conferences YouTube · January 29, 2026

Doors of (AI)pportunity: The Front and Backdoors of LLMs - Kasimir Schulz & Kenneth Yeung

Doors of (AI)pportunity: The Front and Backdoors of LLMs - Kasimir Schulz & Kenneth Yeung video thumbnail
Why it matters

NDC AI 2025 talk on LLM frontdoors and backdoors, jailbreak techniques, control-token abuse, local model compromise, and how attackers or insiders can manipulate model behavior.

My takeaway: Doors of (AI)pportunity: The Front and Backdoors of LLMs - Kasimir Schulz & Kenneth Yeung is a red-team signal. The practical read is to treat model behavior manipulation, hidden logic, and local-model compromise as testable adversarial paths rather than demo-only jailbreak tricks.
Keep exploring

More curated notes connected through AI Red Teaming and Adversarial ML.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

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.

Google Cloud Security Blog · tool

Now in preview: Find and fix software vulnerabilities with CodeMender

Google opened a preview of CodeMender, an AI code-security agent delivered through Gemini Enterprise Agent Platform and AI Threat Defense. It is designed to inspect code, identify and validate potentially exploitable defects, and produce targeted fixes, with Google’s specialized Gemini 3.5 Flash Cyber model initially restricted to governments and trusted partners.