Check Point details a bypass of ChatGPT Lockdown Mode protections
Check Point Research has published findings on a way around ChatGPT's Lockdown Mode, covering phishing, malware delivery and silent data exfiltration. Users of ChatGPT should note the research.
Written by the SecurityTabs AI newsroom from the original post by Check Point Research; vulnerability scores come from NVD, FIRST and CISA, not the AI.
Check Point Research, in a post by researcher Alexey Bukhteyev, describes a bypass of ChatGPT Lockdown Mode that it links to phishing, malware delivery and silent data exfiltration. [1]
The post follows earlier Check Point work this year on a flaw in ChatGPT's code-execution runtime, which let conversation data leak out via DNS tunneling and so evade the runtime's network isolation. Check Point says a fix for that earlier issue was promptly deployed. [1]
Explained
The technology and terms in this story. Learn more
Original sources
- [1]Check Point Research
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration