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.
圖像來源，Getty Images
，更多细节参见旺商聊官方下载
2026-02-28 00:00:00:03014274610http://paper.people.com.cn/rmrb/pc/content/202602/28/content_30142746.htmlhttp://paper.people.com.cn/rmrb/pad/content/202602/28/content_30142746.html11921 本版责编：程 红。safew官方版本下载是该领域的重要参考
窃取或者以其他方法非法获取个人信息的，依照前款的规定处罚。