Security researchers unveil deepfake AI audio attack that hijacks live conversations

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.

Read more

Source: https://cointelegraph.com/news/security-researchers-unveil-deepfake-artificial-intelligenceai-audio-attack-hijacks-live-conversations