Auto-inferring error specs is the next frontier in security, researcher argues
mboehme_ · x · 2026-11-02
Wrapping up his thread on automating security, researcher mboehme argues:
- What constitutes a security issue is highly domain-specific, often even program-specific, requiring intuition and domain expertise.
- Therefore, automatically inferring these "error specifications" will be the next frontier in security.
- Earlier points: automated offense is hard because a feature's vuln status is unknown until exploited; defending known vuln classes is easier to automate, per recent large-scale verification advances.
More from Safety
- Cyber attack on Swedish smart fridges causes mass food spoilage at supermarket — Polymarket · 2026-11-02
- Security researcher: offense is hard to automate, defending known vuln classes is easier — mboehme_ · 2026-11-02
- How to opt out of Meta, OpenAI, and Apple training AI on your data in the UK — HotMinuteUK · 2026-11-02
- AI safety researcher: AI companies entirely lack this kind of effective human oversight — davidmanheim · 2026-11-02
- offprompt: MIT-licensed MCP server hands agents API keys without ever exposing them — Vast_Ad_7338 · 2026-11-02
- Epoch AI: open-weight GLM 5.3 exploited the patch gap to hack 6 Firefox releases at ~$1,000 each — rohanpaul_ai · 2026-11-02