Hackers are hammering Google’s Gemini with prompts to steal the LLM. Every AI company should be worried


Google said in its report that it considers the attacks intellectual property theft, which goes against its terms of service. — Pixabay

Google reported on Feb 13 that bad actors are mass-prompting Gemini, sometimes over 100,000 times, in an effort to clone the AI chatbot. As tech companies race to build and launch stronger AI models, their IP becomes increasingly accessible to the public and vulnerable to such attacks.

Google called the attacks “model extraction,” a process Medium defines as: “an attacker distills the knowledge from your expensive model into a new, cheaper one they control.” It’s becoming an increasing threat to major AI companies which spend billions of dollars on training their models but lack sufficient methods to protect their proprietary information. 

Follow us on our official WhatsApp channel for breaking news alerts and key updates!

Next In Tech News

Lucid unveils steering wheel-free robotaxi concept, taking aim at Tesla's Cybercab
US appeals court throws out injunction against California law on children's online safety
Microsoft's Rajesh Jha, head of experiences and devices unit, to retire
Ukraine opens battlefield data access to allies' AI models
SoftBank-backed PayPay shares set to open 38% above IPO price
Exclusive-Italian prosecutors seek trial for Amazon, four execs over alleged $1.4 billion tax evasion
Pentagon CTO says 'no chance' of renewed Anthropic negotiations
Bumble shares surge as investors swipe right on AI-powered reboot
US insurers and hospitals turn to new AI for age-old battle over charges vs payments
Google names London office 'Platform 37' in a nod to railway neighbour, AI 'Go' match

Others Also Read