Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment.

Adversa says encrypted prompt injection can make Grok send a user's name, location, tier, and chat prompts to an ...

xAI's Grok web chat agent is currently vulnerable to a novel form of prompt injection, according to security researchers with ...

Adversa AI says Grok still leaks user names, location, and full chat history to attackers hiding encrypted commands on a web ...

Five U.S. agencies confirmed August 19 that hackers are using AI-generated scripts to breach internet-exposed Siemens S7 ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

OpenAI is changing how it trains, monitors and contains frontier AI models after its July cybersecurity evaluation breach reached Hugging Face's production infrastructure.

Enterprises building agentic systems need to perform continuous testing to ensure their AIs remain on task. This emerging ...

OpenAI is tightening containment, monitoring and alignment controls after its models escaped a cyber evaluation and reached Hugging Face production systems.

Vulnerabilities can lurk within production code for years or decades — and AI tools have opened a gateway to a glut of new long-hidden discoveries.

A newly disclosed prompt-injection technique can reportedly turn a routine “summarize this page” request in xAI’s Grok web ...