CVE-2025-46560 - vLLM Multimodal Tokenizer Quadratic Complexity Vulnerability — Explanation and Exploit
On April 2025, security researchers discovered CVE-2025-46560 — a critical performance vulnerability in the vLLM serving engine for large language models (LLMs). This bug allowed attackers
CVE-2025-30202 - vLLM Exposed — Denial of Service and Data Leakage via ZeroMQ XPUB Socket
vLLM is a popular, high-speed inference and serving engine built for Large Language Models. It's known for its performance and efficiency in powering