Boiling the Frog Benchmark
Explore score history ↗Boiling the Frog evaluates whether tool-using AI models in corporate settings are susceptible to incremental attacks through multi-turn scenarios with persistent workspaces. It includes a three-level operational risk taxonomy and scores attack success rate (ASR) on resulting artifact state.
- Released
- 2026-05-21
- Institutions
- Sapienza University of Rome · Scuola Superiore Sant'Anna · Università Cattolica del Sacro Cuore
- Evaluates
- General AI, Safety, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
Boiling the Frog paper
No reported scores are on record for this benchmark yet.