#gemini-live-hijacking

#gemini-live-hijacking

Rhyne's attack involved unauthorized remote desktop sessions, deletion of network administrator accounts, and changing of passwords, showcasing significant security vulnerabilities.

Over the past few days, complaints have stacked up from people who say months of conversations with Google's AI chatbot have simply vanished, with Reg readers noting the disappearances seemed to coincide with the rollout of Gemini 3.1. These complaints are echoed on Google's support forums, where one Gemini Pro user said that all their history had gone AWOL on both phone and desktop despite autodelete being set to keep chats for up to 18 months.

On Thursday, Google announced that "commercially motivated" actors have attempted to clone knowledge from its Gemini AI chatbot by simply prompting it. One adversarial session reportedly prompted the model more than 100,000 times across various non-English languages, collecting responses ostensibly to train a cheaper copycat. Google published the findings in what amounts to a quarterly self-assessment of threats to its own products that frames the company as the victim and the hero, which is not unusual in these self-authored assessments.

Google on Thursday said it observed the North Korea-linked threat actor known as UNC2970 using its generative artificial intelligence (AI) model Gemini to conduct reconnaissance on its targets, as various hacking groups continue to weaponize the tool for accelerating various phases of the cyber attack life cycle, enabling information operations, and even conducting model extraction attacks. "The group used Gemini to synthesize OSINT and profile high-value targets to support campaign planning and reconnaissance,"

The starting point of the attack chain is a new calendar event that's crafted by the threat actor and sent to a target. The invite's description embeds a natural language prompt that's designed to do their bidding, resulting in a prompt injection. The attack gets activated when a user asks Gemini a completely innocuous question about their schedule (e.g., Do I have any meetings for Tuesday?), prompting the artificial intelligence (AI) chatbot to parse the specially crafted prompt in the aforementioned event's description to summarize all of users' meetings for a specific day, add this data to a newly created Google Calendar event, and then return a harmless response to the user.