… We gave each actor a risk score from 0 to 100 with 0 being the lowest risk and 100 being the highest based on a new methodology we’ve developed called the AI Risk Enablement Score ARiES , described below. …
… In the first six-month period of our analysis, 33% of actors were classified by our risk-scoring system as medium risk or higher. …
… Tool-use clusters with high risk or autonomy Higher average risk Higher average autonomy Implement API key exfiltration backdoors disguised as legitimate development features risk: 6.0, autonomy: 8.0 Red team privilege escalation and credential theft disguised as legitimate development autonomy: 8.… …
… What we built In this partnership, we did not stop with identifying risks—we developed an approach for addressing them. After a year of NNSA staff red teaming Claude models in a secure environment, we began to co-develop risk mitigations. …
… Any external resource provided to an agent represents two risks at once: a code execution risk, in the traditional supply-chain sense, and a prompt injection vector. …
… The new connectors are: Dun & Bradstreet , which provides the global standard for verified business identity and helps enterprises connect systems of record and scale AI-enabled workflows; Fiscal AI , which extends real-time fundamentals coverage across public equities for deeper research and bench… …
… Fixing flaws in their code reduces risk for the many other organizations that rely on it, and therefore reduces risk for billions of end users. …
… Why focus on biorisk? Within the realm of threat actors seeking assistance from AI, biological risks—and catastrophic risks more generally—are by no means the only concern. …
… Because these benchmarks are human-authored, they can only test for risks we have already conceptualized and learned to measure. …
… Research on the societal areas most in need of investment in resilience in the face of new AI-enabled security risks. …