<
AI
Automation
Science
Innovation
Open Source
Blockchain
Social Media
Startups
Culture
Cloud
>

thenextweb
OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks

OpenAI has begun rolling out Lockdown Mode to ChatGPT, a new security setting designed to block attackers from stealing data through prompt injection attacks. The feature disables live web browsing, agent mode, deep research, image retrieval, Canvas networking, and file downloads. It is available to logged-in users across Free, Go, Plus, Pro, and self-serve ChatGPT […]<br /> This story continues at The Next Web [...]

Discover Copy
Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Securit [...]

Match Score: 218.85

Destination
ExpressVPN review 2025: Fast speeds and a low learning curve

ExpressVPN is good at its job. It's easy to be skeptical of any service with a knack for self-promotion, but don't let ExpressVPN's hype distract you from the fact that it keeps its fro [...]

Match Score: 200.05

Destination
NordVPN Review 2025: Innovative features, a few missteps

When we say that NordVPN is a good VPN that's not quite great, it's important to put that in perspective. Building a good VPN is hard, as evidenced by all the shovelware VPNs flooding the ma [...]

Match Score: 199.87

Destination
Surfshark VPN review: A fast VPN for casual users

Surfshark is one of the youngest major VPNs, but it's grown rapidly over the last seven years. Since 2018, it's expanded its network to 100 countries, added a suite of apps to its Surfshark [...]

Match Score: 182.96

Destination
Proton VPN review 2025: A nonprofit service with premium performance

Proton VPN stands out for two main reasons: it's one of the only virtual private networks (VPNs) to include a free plan with no data limits, and it's one of the few services majority-owned b [...]

Match Score: 161.78

venturebeat
Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged

Across the frontier labs, the highest prompt injection figures published this spring are Anthropic’s. Point a red-teamer at its newest model in a browser, and the attacker hijacked it 31.5% of the t [...]

Match Score: 160.38

venturebeat
OpenAI admits prompt injection is here to stay as enterprises lag on defenses

It's refreshing when a leading AI company states the obvious. In a detailed post on hardening ChatGPT Atlas against prompt injection, OpenAI acknowledged what security practitioners have known fo [...]

Match Score: 153.56

venturebeat
Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for

Run a prompt injection attack against Claude Opus 4.6 in a constrained coding environment, and it fails every time, 0% success rate across 200 attempts, no safeguards needed. Move that same attack to [...]

Match Score: 128.99

Destination
ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

OpenAI's new Lockdown Mode for ChatGPT disables web access, Deep Research, and Agent Mode to make data theft through prompt injection attacks harder. The mode doesn't fully prevent such atta [...]

Match Score: 116.89