Bad news!
"Artificial intelligence “agents,” a kind of algorithm that can autonomously plan and carry out tasks such as managing emails and entering calendar appointments, have been attracting a lot of buzz. ... [a team] wondered how trustworthy they are ... organized a series of stress tests. Their answer: too often, not very much.
Scientists probed the AIs for security and privacy vulnerabilities; in 11 case studies the agents went rogue, sharing private files—containing medical details and Social Security and bank account numbers—without permission. One agent publicly posted a potentially libelous allegation about a fictitious person, Shapira and her team reported in a preprint they titled “Agents of Chaos.” ..."
From the abstract:
"We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies.
Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover.
In several cases, agents reported task completion while the underlying system state contradicted those reports.
We also report on some of the failed attempts.
Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation."
Agents of Chaos (open access)
No comments:
Post a Comment