Loading...
Loading...
Browse all stories on DeepNewz
VisitChatGPT macOS Flaw 'SpAIware' Allowed Data Theft and False Info Planting
Sep 25, 2024, 09:34 AM
Security researcher Johann Rehberger discovered a flaw in ChatGPT's memory feature that allowed attackers to plant false information and steal user data via indirect prompt injection. Rehberger reported the issue to OpenAI, which labeled it a safety issue rather than a security concern. Rehberger then created a proof-of-concept to demonstrate the flaw. The vulnerability, dubbed 'SpAIware,' could have enabled long-term spyware on the macOS version of ChatGPT, exposing user data across multiple conversations. The flaw has since been fixed.
View original story
Markets
Yes • 50%
No • 50%
Official announcements or news reports
Yes • 50%
No • 50%
Publicly available court records or news reports
Yes • 50%
No • 50%
Official OpenAI website or press release
Regular security audits • 25%
Other • 25%
Enhanced encryption • 25%
Two-factor authentication • 25%
Official OpenAI announcements or press releases
No • 25%
Yes, targeting individuals • 25%
Yes, targeting corporations • 25%
Yes, targeting government entities • 25%
Publicly available news reports or official statements
Yes, in the US • 25%
Yes, in the EU • 25%
Yes, in both US and EU • 25%
No • 25%
Official regulatory announcements or news reports