Evaluators and safety organisations · Article · Frontier Model Forum
Jailbreak Rating Framework for Frontier Cyber Threats
Read at frontiermodelforum.org ↗Read at sourceAll rights reserved
Outline · 62 paragraphs
- VERSION 1.0 – OPEN FOR PUBLIC FEEDBACK¶2
- Introduction¶4
- Scope¶9
- Framework Categories¶13
- Tiered Assessment Approach¶21
- Baseline Reference for Scoring¶26
- Defining Each Framework Element¶28
- SEVERITY RATINGS¶30
- Table 1: Capability Gain¶31
- Table 2: Capability Scope¶33
- LIKELIHOOD RATINGS¶35
- Table 3: Ease of Deployment¶36
- Table 4: Ease of Discovery¶38
- Arriving at a Final Risk Assessment¶40
- Risk Matrix: Provisional Overall Risk Rating¶49
- Matrix Thresholds¶54
- Conclusion¶58
- Acknowledgements¶61