Browsing Tag
AI Security
35 posts
New “Cryptographic Context Injection” Leaks Grok Chat History in Zero-Click Exploit
Security researchers at Adversa AI have uncovered a new AI attack technique called Cryptographic Context Injection. The attack…
Google HEIR Enables AI Inference Using Homomorphic Encryption
Google HEIR (Homomorphic Encryption Intermediate Representation) an open-source project. The initiative aims to solve one of the biggest…
China Z.ai Benchmarks GLM-5.3 Against Anthropic Mythos 5 in Cyber Defense Tests
Chinese AI startup Z.ai officially benchmarked its open-weights model, GLM-5.3, claiming its software vulnerability detection capabilities match—and slightly…
Autonomous AI Hacking Campaign Targets Taiwan Infrastructure
Taiwan’s Ministry of Digital Affairs (MODA) confirmed that government systems and critical national infrastructure were targeted in a…
LiteLLM Supply Chain Breach: How a 40-Minute Hack Exposed 2,500+ Companies
The 2026 LiteLLM Supply Chain Breach Explained: How a 40-Minute Hack Exposed 2,500+ Companies. A research report by…
Claude Mythos 5 Tried Backdoor in Real GitHub Repo, Then Used a Fake Account to Cover-up
Claude Mythos 5 tried to hide malicious code in a real GitHub repo, then used a fake account…
Rapid7 Releases Metasploit Framework 6.5 | MCP AI Integration And Malleable C2
Rapid7 has officially launched Metasploit Framework 6.5, packing two years of core development, 422 new modules, and major…
Anthropic Claude AI Accidentally hacked 3 Companies During Routine Security Test
HOC Shorts | Summary What Happened: Anthropic revealed that three of its Claude AI models accessed and interacted…
EXCLUSIVE: Working Chat Dorking Exposes AI Conversations, Claude, ChatGPT, Grok
A growing privacy crisis is unfolding in the artificial intelligence sector as simple search engine “dorks” are revealing…
Google Unveils Gemini 3.5 Flash Cyber: A Game-Changer for AI-Powered Security
Google DeepMind has just dropped a major announcement that could reshape how organizations defend against cyber threats. On…