Confidence Conference
Confidence is a deeply technical audience — the right room for threat modeling, AI security and cloud attack-path material with no marketing layer.
Updated
Recorded talk: threat modeling at Allegro scale
The talk covers how STRIDE threat modeling was rolled out across a large e-commerce engineering organisation while I led the cloud security work stream at Allegro: how sessions were scoped so a team could finish one, how findings were turned into tickets with owners, and which parts of the textbook process had to be dropped to get adoption.
Topics I bring to this audience
- Threat modeling AI features with STRIDE, including the AI-specific STRIDE adaptation I built for GenAI systems at Allegro
- Prompt injection and agent authority in production LLM systems
- Identity attack paths across hybrid Entra ID and Active Directory
Watch the recording
Related
Threat modeling
A practical STRIDE-based threat modeling method for cloud, application and AI systems, built to be run by engineering teams.
Threat modeling
Facilitated STRIDE threat modeling on your real architecture, plus the templates and coaching to keep teams doing it without me.
STRIDE for AI systems
Applying STRIDE to LLM and agentic applications: what each category means when untrusted text can act as instructions, where STRIDE stops covering multi-agent failure modes, and the controls per element.
Oh My Hack
Recorded Oh My Hack 2024 talk (Polish): modelowanie zagrożeń w skali Allegro — od STRIDE do sukcesu.
AI security assessment
Security assessment of GenAI and LLM systems: prompt injection, tool and agent abuse, data leakage, model supply chain and monitoring gaps.
AI security
How to secure GenAI, LLM and agentic AI systems: current OWASP threat classes, layered controls, agent authority, retrieval isolation and monitoring.