T. Rowe Price Expands Claude Across Investment Teams and Developers24m ago Val Bercovici, Chief AI Officer at WEKA – Interview Series32m ago Ben Jennings on the Bayeux tapestry – cartoon32m ago The latest Avatar: Seven Havens trailer gives us a deeper dive into the characters and story33m ago Agentic AI Is The New Attack Surface: How Can SAP Application Security Teams Repel It?34m ago Pony.ai Starts Fully Driverless Robotaxi Passenger Tests in Zagreb36m ago Euno raises $23m to give enterprise AI agents the context they lack37m ago Nvidia’s Huang Touts Cybersecurity as Next Big Market for AI41m ago Universal Music is launching an AI music platform with ElevenLabs47m ago Red Hat AI 3.5 tackles the GPU queue that can stall AI pilots48m ago Moonshot Secretly Routed User Requests Through Claude, Anthropic Says49m ago A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises49m ago Governments are turning to Claude to automate spying49m ago Anthropic Says It Blocked Possible Efforts to Build Biological Weapons49m ago

T. Rowe Price Expands Claude Across Investment Teams and Developers24m ago Val Bercovici, Chief AI Officer at WEKA – Interview Series32m ago Ben Jennings on the Bayeux tapestry – cartoon32m ago The latest Avatar: Seven Havens trailer gives us a deeper dive into the characters and story33m ago Agentic AI Is The New Attack Surface: How Can SAP Application Security Teams Repel It?34m ago Pony.ai Starts Fully Driverless Robotaxi Passenger Tests in Zagreb36m ago Euno raises $23m to give enterprise AI agents the context they lack37m ago Nvidia’s Huang Touts Cybersecurity as Next Big Market for AI41m ago Universal Music is launching an AI music platform with ElevenLabs47m ago Red Hat AI 3.5 tackles the GPU queue that can stall AI pilots48m ago Moonshot Secretly Routed User Requests Through Claude, Anthropic Says49m ago A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises49m ago Governments are turning to Claude to automate spying49m ago Anthropic Says It Blocked Possible Efforts to Build Biological Weapons49m ago

Cybersecurity LLM & Text Generation

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

Covered by 3 sourcesPublished Jun 6, 2026

OpenAI has introduced Lockdown Mode, a security feature designed to shield sensitive data from prompt injection attacks by restricting model behavior and external inputs. This mode aims to enhance data protection for users handling confidential information.

Covered by 3 sources

#data-security #lockdown-mode #openai #prompt-injection-attacks

More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 2 sources9h ago

Chinese AI Giants Accused of Sending Millions of User Queries to U.S. Models

The Wall Street Journal49m ago

Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources11h ago