The AI was able to manipulate a live conversation between two people without either noticing.
IBM Security researchers recently discovered a “surprisingly and scarily easy” technique to hijack and manipulate live conversations using artificial intelligence (AI).
The attack, called “audio-jacking,” relies on generative AI — a class of AI that includes OpenAI’s ChatGPT and Meta’s Llama-2 — and deepfake audio technology.
In the experiment, researchers instructed the AI to process audio from two sources in a live communication — such as a phone conversation. Upon hearing a specific keyword or phrase, the AI is further instructed to intercept the related audio and manipulate it before sending it on to the intended recipient.
