Reference · model-evaluation-research
AI Security Institute — Research Blog
Primary research from the UK AI Security Institute (DSIT): frontier-model cyber-capability evaluations, safeguard and jailbreak testing, and incident reports from their own agent testing.
More references
- [un]prompted 2026 slide archiveai-security-programCommunity GitHub archive of 49 slide decks from [un]prompted 2026, the AI Security Practitioner Conference (March 3-4, San Francisco), spanning AI governance, agent security, offensive AI and agent evaluation; no licence stated.
- AboutSecurity (WgpSec)pentest-knowledge-baseA structured penetration-testing knowledge base by the WgpSec team, packaged for consumption by AI agents: 200+ attack-chain methodologies (recon through post-exploitation, cloud, code audit, CTF, malware analysis, lateral movement), password/fuzzing dictionaries, exploit payloads for SQLi/XSS/SSRF, and a 600+ entry vulnerability database organized by product. It is the knowledge layer of the WgpSec agentic pentest ecosystem (MCP server + autonomous agent).
- AI Megalistreference-indexMIT-licensed curated index of 225+ general-purpose AI tools (chat, coding, research, image, video, voice, agents, local model runners) with a per-tool writeup page; a general AI directory with no security-specific content.
- AI Security Made Easy — Rob van der Veer (SANS AI Cybersecurity Summit 2025)ai-security-programSlide deck from the SANS AI Cybersecurity Summit 2025 by Rob van der Veer of the Software Improvement Group, framing six ways AI security differs from standard security plus the AI-specific threats and controls it names.
- AI Security Maturity Model (AISMM)ai-security-programCloud Security Alliance maturity model for an enterprise AI security program: 12 categories across three domains, five CMM levels and 120 KPI control objectives mapped to the AI Controls Matrix, plus a spreadsheet and poster.
- AI Security Maturity Model: A CISO Roadmapai-security-programVendor blog post from BeyondScale Technologies setting out a five-level AI security maturity model mapped to NIST AI RMF tiers and OWASP LLM Top 10 entries, with a five-question self-assessment and a per-level action plan.