An AI agent spent 16 hours hacking Stanford's network. It outperformed human pros for much less than their six-figure salaries.

"For 16 hours, an AI agent crawled Stanford's public and private computer science networks, digging up security flaws across thousands of devices. By the end of the test, it had outperformed professional human hackers - and at a fraction of the cost. A study published Wednesday by Stanford researchers found that their AI agent, ARTERMIS, placed second in an experiment with 10 selected cybersecurity professionals."

"The researchers said the agent could uncover weaknesses that humans missed and investigate several vulnerabilities at once. Running ARTEMIS costs about $18 an hour, far below the average salary of about $125,000 a year for a "professional penetration tester," the study said. A more advanced version of the agent costs $59 an hour and still comes in cheaper than hiring a top human expert."

An AI agent named ARTEMIS crawled a university computer science network of about 8,000 devices for 16 hours, identifying security flaws across servers, computers, and smart devices. The agent placed second among ten selected cybersecurity professionals and outperformed nine of the ten participants within the comparison window. The agent ran for 16 hours while human testers contributed at least 10 hours; performance comparison was limited to the AI's first 10 hours. ARTEMIS discovered multiple valid vulnerabilities and could investigate several issues in parallel. Operating costs were roughly $18 per hour for the base agent and $59 per hour for an advanced version, significantly lower than typical professional penetration tester salaries.

Read at Business Insider