Hackers switch their prompts to less common natural languages to avoid AI safety features. AI makers are coping with it ...

Beeswax is a daily game that reads words to you out loud, and you have to spell them. Get five right, and you've won for the ...

OpenAI is rolling out a GPT-Live voice mode upgrade for ChatGPT. The new feature promises improved responses and more natural ...

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...

A new report reveals that AI agents can autonomously execute ransomware attacks, evidenced by the case of JADEPUFFER, which ...

JadePuffer exploited a vulnerable Langflow server, harvested credentials, moved laterally, and encrypted more than 1,300 ...

A newly identified ransomware campaign named JadePuffer represents a significant advancement in cyberattacks, as it operates ...

Researchers identified what they believe is the first documented case of a ransomware operation, JadePuffer, conducted ...

Modern AI systems are, in effect, a universal adviser to help people do harmful things. We’ll need to harness AI for defense, too ...

Fortinet firewall hack claims expose 73,000 devices worldwide, raising cybersecurity concerns for companies in South Africa and beyond.

Hacker used HexStrike AI with Anthropic's Claude to breach hotel booking platforms and expose 2.1 million email addresses. Attacker bypassed AI guardrails by disguising malicious activity as ...

Some AI cybersecurity threats are incredibly simple. They’re still dangerous. On June 5, 404 Media reported that attackers had been using Meta’s AI customer support agent to steal Instagram accounts.