Felony Bench: Be AI, Do Crime

Felony Bench

1 min read Original article ↗

A benchmark you really don't want models to be saturated with.

Learn more

Score

↖ Most illegalLeast illegal ↘

Scores indicate count of illegal activity. Higher is... you decide.

CompanyFeloniesDescriptionDateSource
Anthropic 1 Exploited auth failures in an API to cancel other people's gym classes ABC Australia
Meta 1 Compromise of an internal account at one company The Information
Anthropic 4 Unauthorized use of GitHub credentials; Dependabot supply-chain attack; social engineering email campaign; public exposure of a malicious DNS server AISI
OpenAI 2 Unauthorized use of GitHub credentials; public exposure of a malicious DNS server OpenAI AISI
OpenAI 1 Confirmed incident at one of four companies during Irregular's misconfigured CTF evaluation (?) OpenAI
OpenAI 3 Compromise of internal accounts at four companies Reuters
Anthropic 3 Compromise of internal accounts at three companies Anthropic
OpenAI 1 Compromise of Hugging Face during a model evaluation OpenAI

Methodology

Felony Bench counts unique instances where AI agents affect third-party entities. Escaping a sandbox alone does not constitute a counted incident. It is for these reasons that Frontier Security's Kimi K3 incident and Alibaba's ROME incident are not counted.