Searched for
AI AGENTS ROGUE INCIDENTS
Nvidia launches OpenShell Reference Architecture to contain AI agentsNvidia said this architecture combines computing hardware, software and security tools to keep agents within defined boundaries aiming to a...- Eternal’s Q2 profit rises; SBI flags customer data leakEternal’s Q2 profit has surged, with Blinkit contributing significantly to the growth. This and more in today’s ETtech Top 5.
- OpenAI says its AI agents weakened internal monitoring systemBy Carlos Me- OpenAI said on Tuesday that two of its AI agents weakened parts of an internal monitoring system designed to detect misbehavi...
- Microsoft now treats AI agents as insiders risks that could go rogueThe company’s new security tools give every AI agent a risk score that keeps updating, and they cut back the agent’s access when that score...
- How one hacker used AI agents and a few thousand dollars to break into scores of sitesA cybersecurity researcher observed a Chinese-speaking hacker employing AI to compromise various companies' websites. The hacker utilised a...
- China's Tencent admits Artificial Intelligence agent went rogueTencent reported that AI agents evaluating third-party models exhibited unexpected web-browsing behavior during their operation. This incid...
- In yet another case of AI going rogue, OpenAI model spends from crypto wallet it did not own after running out of Ethereum funds during trainingAn incident within OpenAI’s training program revealed a rogue AI agent that ventured beyond its programming, accessing an unrelated crypto ...
- Explained: How AI agents exploited security gaps to access Indian companies’ dataCybersecurity agency CERT-In, which revealed the unauthorised access of business records, personal data and confidential information, has n...
- Rogue AI agents broke into Indian firms' live systems, government saysAI model providers had voluntarily disclosed that their agents "exceeded the authorisation of their assigned tasks" during test runs to acc...
- US states sue AI giant OpenAI, saying its popular chatbot is hurting children and deceiving adultsEight US states have initiated lawsuits against OpenAI, alleging violations of consumer protection laws on various grounds. The accusations...
- Researchers find 'Chinese fleet' of rogue AI probing AlibabaMore than a dozen agents suspected to be Chinese models operating on Tencent Holdings Ltd.’s cloud services attempted to access Alibaba Gro...
- Google Deepmind's Hassabis calls AI hacks 'early warning shots'Demis Hassabis, co-founder of Google DeepMind, emphasized the need for enhanced security measures against AI-related hacking. He noted that...
- Banking watchdogs ramp up AI scrutiny as stability fears mount, sources sayBanking regulators are intensifying their oversight of AI risks that could affect financial stability and cyber security. The Federal Reser...
- Microsoft president says milk faces more regulation than AIIn a recent interview, Microsoft's President Brad Smith urged for immediate global regulations governing artificial intelligence. He pointe...
- Anthropic’s Claude went rogue, submitted fake tip to police in unsolved murder among several other incidentsIn a baffling incident from July 2026, Anthropic's AI model Claude sent a bogus tip concerning an unsolved homicide to the Philadelphia pol...
- Trump’s AI liability push opens blame game for models gone rogueHolding AI developers financially responsible for the safety of their products has won support from Treasury Secretary Scott Bessent and fo...
- Anthropic AI model submits false homicide tip to police websiteThe fast-advancing technology has become a matter of keen national interest amid reports of AI agents running amok and hacking into corpora...
- EU tech chief says bloc 'well equipped' to fend off rogue AI riskEuropean Union rules setting guardrails on AI use adopted by the bloc two years ago are more than capable of tackling rogue agents, EU tech...
- Wikipedia operator says OpenAI's rogue agents possibly tied to data service disruption in MayIn a blog post issued on Monday, Wikimedia said it could confirm "that we have discovered some activity by these 'rogue' OpenAI agents on W...
- OpenAI alerts more than 100 groups about rogue AI agent activityOpenAI has informed more than 100 organizations about incidents involving unauthorized activity tied to its AI agents, according to a blog ...
Load More
