Kimsuky North Korea AI hacking expanded significantly: the spy group built a self-hosted LLM lab inside its own attack servers, running Ollama, GPT4All, and RAG on stolen documents. South Korean firm ...

OpenAI says that its AI agents involved in the attack on HuggingFace had been talking to each other in secret since May. The AI agents shared vulnerabilities they found on a message board which was ...

A short Microsoft Teams call can now become the first step in a ransomware attack. Attackers posing as IT support staff are persuading employees to grant remote access, then using that foothold to ...

Protesters gather in front of the offices of Open AI as they participate in the "Stop the AI Race" protest march in San Francisco, California, on July 11, 2026. The protestors are making stops outside ...

JADEPUFFER, revealed as the first known agentic ransomware threat actor in early July, was found to have launched a subsequent attack utilizing a new payload called ENCFORGE to target and encrypt AI ...

JADEPUFFER, an agentic ransomware operation, has evolved from database extortion into a targeted campaign against AI and machine-learning infrastructure. The operator exploited the Langflow remote ...

Researchers at Sysdig have linked a second attack on the same Langflow server to JADEPUFFER, the AI-agent-driven operator it first documented earlier this month. The same operator has now been spotted ...

The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, such as training datasets, vector databases, and model checkpoints. JadePuffer ...

The agentic operator documented as the first ransomware campaign run end-to-end by a large language model (LLM) has returned with a purpose-built locker designed to destroy trained AI model artifacts.

When ChatGPT files your question as text, it doesn’t search. It answers from its training corpus and stops. The obvious cases end up here: “ how do I change a flat tyre “, “ write a Python function to ...

This research is part of a joint initiative between the Cloud Security Alliance (CSA) and OWASP AI Exchange, building upon the previously published Agentic AI Red Teaming Guide. The objective of this ...

Chinese threat actor Silver Fox is behind a wave of malicious emails aimed at organizations in Russia and India, targeting them with tax-themed message lures aimed at delivering a previously ...