Covered by 2 outlets — first reported by Check Point Research, Nov 5, 14:00 UTC
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration
MentionsOpenAICheck Point
In brief
Research by: Alexey Bukhteyev Key Takeaways Introduction Earlier this year, Check Point Research disclosed a security flaw in ChatGPT’s code-execution runtime that allowed sensitive conversation data to be silently exfiltrated to an attacker-controlled server through DNS tunneling, a hidden outbound channel that bypassed the runtime’s network isolation. A fix for this issue was promptly deployed.
From Check Point Research's coverage.
Continue reading
2 outlets, in the order they reported it.
Check Point ResearchFirst report
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration
Research by: Alexey Bukhteyev Key Takeaways Introduction Earlier this year, Check Point Research disclosed a security flaw in ChatGPT’s code-execution runtime that allowed sensitive conversation data to be silently exfiltrated to an…
The Hacker News
Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction
Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT.
Explained
The technology and terms in this story. Learn more
- AttackPhishingMessages that impersonate someone trusted to get people to click, log in or pay.
- ProtocolDNS · Domain Name SystemThe internet's phone book: it turns names like example.com into the addresses computers connect to.
- ConceptExploitCode or a technique that turns a software flaw into something an attacker can actually use.