Token Injection: Crashing LLM Inference With Special Tokens (opens in new tab)

As large language models \(LLMs\) are deployed at scale, their underlying inference frameworks \(e\.g\., vLLM, SGLang, TensorRT-LLM\) have become critical operational pillars\. These systems must splice user prompts with control structures, tokenise them, and schedule requests within milliseconds\. Within this high-speed pipeline, we identify an underappreciated attack surface: special tokens\. We introduce the first \"Token Injection\" attack model, showing how a single prompt composed solel...