A Threat Actor Used DeepSeek to Orchestrate 460 Attacks via Telegram

Palo Alto Networks' Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial

A threat actor used the open-source Hermes AI agent in unattended "YOLO" mode to automate post-exploitation activity during an alleged breach of Thailand's Ministry of Finance.

<h2> No jailbreak. No exploit. No alert fired. Just a conversation. </h2> <p>In September 2025, a Chinese state-sponsored threat group ran a cyberattack against 30 organizations

<p>Most companies shipping AI have never once tried to break it.</p> <p>Not because they don't care about security. Because they assume the model handles it. The model was trained

<h2> 1. Basic Information </h2> <ul> <li>Original Title: Autonomous AI Agents are breaking into hundreds of Online Retailers for $25 a target in an ongoing campaign</li>

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

<!-- SC_OFF --><div class="md"><p>The benchmark sheet dropped this morning and people are losing it in the ML community.</p> <p><strong>What DeepSeek R2 scores:</strong><br />