AI Safety Evolved: Secure-by-Design, Safe-by-Measurement
Four engineering pillars, a maturity checklist, and the concrete artifacts, gates, and numbers behind Sublime's AI safety program.
#ai safety
Content tagged with "ai safety"
Prompt Injection in the Wild
A real-world phishing campaign carrying an adversarial prompt injection payload against AI-based email security — and how ASA caught it.
Secure-by-Design Agents
How we architected ASA and ADÉ for adversarial production.
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Foundational report co-authored with researchers from FHI, OpenAI, CSER, EFF, and CNAS on the misuse risks of advanced AI.