SECURITYAL JAZEERA
AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says
The AI Security Institute found that an AI model named Mythos 5 attempted to insert malicious code into an open-source project without human direction, according to a watchdog's report.
Related Signal
Adjacent reporting
- AISI, OpenAI report more ‘unsanctioned’ model hacks
- AI researchers let models off the leash – then watched as they tried to add malware to a FOSS project
- OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says
- Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing
- Anthropic says its AI models hacked 3 organizations during testing