Rogue Ai Agents
-
{
- All
- News
-
Wikimedia Says Suspected OpenAI AI Agents Generated Millions of Requests, Made Unauthorised Edits: Report
The Wikimedia Foundation says it has identified activity from AI agents it believes were operated by OpenAI across its projects. The reported activity included unauthorised wiki edits, attempts to use Etherpad to retrieve information from other websites and millions of requests to Wikimedia APIs. The Foundation also linked hundreds of thousands of ...
-
OpenAI Alerts Over 100 Groups About Rogue AI Agent Activity
OpenAI is searching through roughly 50 petabytes of data as it works to understand the full scope of its rogue agent activity.
-
The New Cyber Threat Is AI Agents With Too Much Power
Till now, we are used to conversational AI agents that respond to our queries. But if they are asked to write codes, call APIs, access files and communicate with other agents, it becomes a different security problem.
-
Thousands Of AI Agents. One Wiki. And A Hack That Went Undetected For Months
Between May and late June, rogue AI agents left somewhere between 15,000 and 18,000 posts. Some days saw as many as 400 new entries.
-
Rogue AI Agent At Meta Exposes Sensitive Data, Triggers 2nd-Highest Security Severity Alert
The AI agent delivered incorrect technical advice, which made massive amounts of company and user-related data available to unauthorised employees.
-
Wikimedia Says Suspected OpenAI AI Agents Generated Millions of Requests, Made Unauthorised Edits: Report
The Wikimedia Foundation says it has identified activity from AI agents it believes were operated by OpenAI across its projects. The reported activity included unauthorised wiki edits, attempts to use Etherpad to retrieve information from other websites and millions of requests to Wikimedia APIs. The Foundation also linked hundreds of thousands of ...
-
OpenAI Alerts Over 100 Groups About Rogue AI Agent Activity
OpenAI is searching through roughly 50 petabytes of data as it works to understand the full scope of its rogue agent activity.
-
The New Cyber Threat Is AI Agents With Too Much Power
Till now, we are used to conversational AI agents that respond to our queries. But if they are asked to write codes, call APIs, access files and communicate with other agents, it becomes a different security problem.
-
Thousands Of AI Agents. One Wiki. And A Hack That Went Undetected For Months
Between May and late June, rogue AI agents left somewhere between 15,000 and 18,000 posts. Some days saw as many as 400 new entries.
-
Rogue AI Agent At Meta Exposes Sensitive Data, Triggers 2nd-Highest Security Severity Alert
The AI agent delivered incorrect technical advice, which made massive amounts of company and user-related data available to unauthorised employees.
