Source: SecurityWeek
The recent zero-click attack method identified by researchers known as ShadowLeak specifically targeted OpenAI’s ChatGPT. This vulnerability has raised significant concerns about the security of AI technologies and the potential risks involved in server-side operations.
Addressing such vulnerabilities is critical as they can lead to unauthorized access to sensitive data, jeopardizing privacy and security for users. The implications of this attack extend beyond OpenAI, highlighting a broader risk across the AI landscape where similar models may be susceptible to exploitation.
👉 Pročitaj original: SecurityWeek
