InfoQ

Anthropic Finds LLMs Can Be Poisoned Using Small Number of Documents

Anthropic's Alignment Science team released a study on poisoning attacks on LLM training. The experiments covered a range of ...

New AI browsers read, click and summarize for you — but experts warn they’re vulnerable to dangerous ‘prompt injections.' Here's how to stay safe

They’re smart, fast and convenient — but AI browsers can also be fooled by malicious code. Here’s what to know before you try ...
Futurism

Malware Is Now Using AI to Rewrite Its Own Code to Avoid Detection

Researchers at Google have discovered that hackers are creating malware that can harness the power of AI during its execution ...

Malicious NuGet packages drop disruptive 'time bombs'

Several malicious packages on NuGet have sabotage payloads scheduled to activate in 2027 and 2028, targeting database ...

ClickFix attacks just got a major upgrade to trick you into infecting your computer with malware — don't fall for this

ClickFix style attacks now includes video tutorials and OS recognition in order to fool victims into downloading malware onto ...

The Next Cyber Battlefield: Why AI-Driven Vibe Hacking Demands A New DevSecOps Mindset

In order to meet this challenge, organizations must redefine DevSecOps not simply as "shift-left security" but as trust-layer ...