The new DDoS: Unicode confusables can't fool LLMs, but they can 5x your API bill Can pixel-identical Unicode homoglyphs fool LLM contract review? I tested 8 attack types against GPT-5.2, Claude Sonnet 4.6, and others with 130+ API calls. The models read through every substitution. But confusable characters fragment into multi-byte BPE tokens, turning a failed comprehension attack into a 5x billing attack. Call it Denial of Spend.
This story was originally featured on Fortune.com
。快连下载安装对此有专业解读
我写下这些，不只是为了追问“银行的风控在哪里”，更希望所有人能从中看到——真正的防线，从来不是App、不是验证码，而是家人之间的理解与信任。
let pixel = image.get(0, 0);