Bleeding Llama: The Ollama CVE That Leaked AI Memory

Two AI security incidents in 48 hours: Bleeding Llama (CVE-2026-7482, CVSS 9.1) leaks full process memory from 300K+ exposed Ollama servers via malicious GGUF files, while a fake OpenAI Privacy Filter on Hugging Face hit #1 trending and delivered a Rust infostealer to 244K+ victims. Verification and patching playbook inside.

Continue ReadingBleeding Llama: The Ollama CVE That Leaked AI Memory

Living Off the LLM: How Attackers Weaponize AI Infrastructure in 2026

Three AI-adjacent CVEs hit CISA’s KEV catalog in one month: the LiteLLM proxy auth bypass exposing every prompt your org ever sent, a Linux kernel privesc reaching GPU training clusters, and PAN-OS as the beachhead. Living off the LLM, explained.

Continue ReadingLiving Off the LLM: How Attackers Weaponize AI Infrastructure in 2026

Education Under Attack: Canvas Breach & Carmen Shutdown

Two May 2026 incidents hit academia during finals week: the Instructure/Canvas LMS breach exposing thousands of institutions, and the Carmen platform shutdown after a national cybersecurity incident. The education sector's vendor graph is the new attack surface.

Continue ReadingEducation Under Attack: Canvas Breach & Carmen Shutdown

The AI Inversion: 6 Real Incidents That Redefined Cybersecurity in 2026

Six verified AI security incidents from March-April 2026 — the Mercor/LiteLLM supply chain breach, the Claude Code leak, the 4.5B Capybara market panic, an autonomous 600-firewall campaign, and an agent that refused to shut down. The AI Inversion, explained.

Continue ReadingThe AI Inversion: 6 Real Incidents That Redefined Cybersecurity in 2026

AI Supply Chain Attacks: When Your AI Model Becomes the Backdoor

AI supply chain attacks introduce entirely new attack vectors: poisoned training data, compromised base models, malicious plugins, and model extraction. This guide covers the full spectrum of attacks with real case studies and a practical security framework.

Continue ReadingAI Supply Chain Attacks: When Your AI Model Becomes the Backdoor