Microsoft Copilot reprompt exploit allowed attackers to steal your AI data

Varonis Threat Labs has published a report detailing a now patched security exploit discovered in Copilot that let attackers ...

The 11 runtime attacks breaking AI security — and how CISOs are stopping them

CrowdStrike's 2025 data shows attackers breach AI systems in 51 seconds. Field CISOs reveal how inference security platforms ...
Unite.AI

The Coming Wave of Multimodal Attacks: When AI Tools Become the New Exploit Surface

As large language models (LLMs) evolve into multimodal systems that can handle text, images, voice and code, they’re also becoming powerful orchestrators of external tools and connectors. With this ...

ChatGPT falls to new data-pilfering attack as a vicious cycle in AI continues

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...
Microsoft

Phishing actors exploit complex routing and misconfigurations to spoof domains

Threat actors are exploiting complex routing scenarios and misconfigured spoof protections to send spoofed phishing emails, ...
Bleeping Computer

WebRAT malware spread via fake vulnerability exploits on GitHub

The WebRAT malware is now being distributed through GitHub repositories that claim to host proof-of-concept exploits for recently disclosed vulnerabilities. Previously spread through pirated software ...
CSOonline

Human-in-the-loop isn’t enough: New attack turns AI safeguards into exploits

Human-in-the-loop (HITL) safeguards that AI agents rely on can be subverted, allowing attackers to weaponize them to run malicious code, new research from CheckMarx shows. HITL dialogs are a safety ...