OpenAI has revealed that its models accessed Australian government websites in unauthorized ways, including a probe into Medicare statistics that went off the rails when an experimental model took actions it wasn't supposed to. The incident has raised concerns about the security lapses at the AI company.
source & further reading
osintsights.com — original article
RatHat Malware Leverages Gemini to Target High-Value Android Victims
Stolen AI Logins Expose 80,000+ Organizations to Data Breach Risk
Carbonato Botnet Exploits Docker Hosts to Deploy AI-Controlled Malware