Evaluating Security Risk in DeepSeek and Other Frontier Reasoning Models

The performance of DeepSeek models has made a clear impact, but are these models safe and secure? We use algorithmic AI vulnerability testing to find out.

Researchers Uncover 'LLMjacking' Scheme Targeting Cloud-Hosted AI Models

Cybersecurity researchers have discovered a novel attack that employs stolen cloud credentials to target cloud-hosted large language model (LLM) services with the goal of selling access to other threat actors. The attack technique has been codenamed LLMjacking by the Sysdig Threat Research Team. "Once initial access was obtained, they exfiltrated cloud credentials and gained