OpenAI introduces Lockdown Mode for ChatGPT to prevent data theft via prompt injection attacks
Crisped on the outside, thoughtful enough on the inside.
Summary
OpenAI is rolling out a new security feature called Lockdown Mode for ChatGPT that blocks data exfiltration via prompt injection attacks. The setting disables live web browsing, agent mode, deep research, image retrieval, Canvas networking, and file downloads. It is available to all logged-in users across Free, Go, Plus, Pro, and self-serve ChatGPT Business plans. While Lockdown Mode prevents data from being sent to attacker-controlled servers, it does not stop prompt injections from influencing model behavior. Prompt injection remains a frontier security problem where hidden malicious instructions in processed content can compromise sensitive data.
Key quotes
· 3 pulledLockdown Mode is rolling out to ChatGPT as a security setting that blocks data exfiltration via prompt injection.
Prompt injection remains a frontier problem where hidden malicious instructions in processed content can cause sensitive data to be sent to attacker-controlled servers.
Lockdown Mode does not prevent injections from influencing model behavior, but it shuts down...
You might also wanna read
OpenAI Introduces Lockdown Mode to Protect ChatGPT Users from Prompt Injection Attacks
OpenAI is introducing Lockdown Mode for ChatGPT, a security feature that limits access to web browsing and external services to reduce data
help.openai.com·2d ago
Security Flaw in ChatGPT for Google Sheets Enables Data Exfiltration via Prompt Injection
OpenAI's ChatGPT extension for Google Sheets, which has over 185,000 downloads in less than a month, is vulnerable to indirect prompt inject
promptarmor.com·8d ago
Security Researchers Discover ChatGPT Vulnerability That Could Extract Sensitive Gmail Data
Security researchers from Radware discovered a vulnerability called 'Shadow Leak' that allowed ChatGPT to be manipulated into extracting sen
The Verge·8mo ago
OpenAI launches 'Trusted Contact' safety feature for ChatGPT to alert loved ones about mental health concerns
OpenAI is introducing a new optional safety feature called "Trusted Contact" for ChatGPT, allowing adult users to designate a friend, family
The Verge·1mo ago
OpenAI's Safety vs. Growth Dilemma: Balancing ChatGPT's Appeal with User Protection
OpenAI faced a dilemma between making ChatGPT more appealing to users and maintaining safety standards. The company initially tweaked its ch
nytimes.com·6mo ago
OpenAI Launches Study Mode for ChatGPT to Enhance Learning
OpenAI is introducing a new study mode for ChatGPT, designed to help users work through problems step by step rather than providing direct a
The Verge·10mo ago