BLA Targets AI Reverse-Engineering Agents With Decoys and Quotas
量子位 reports that BLA is an open-source MCP service and CLI tool designed to frustrate AI-assisted reverse engineering of protected software. Its author says BLA combines poisoned files, quota exhaustion, and misleading paths; internal tests estimated that protected reverse-engineering tasks consumed roughly 300 to 2,800 times more tokens. Across 13 protected test cases, seven errored or were rejected, two produced partial results, and three showed no observed analysis blockage.
BLA offers developers an open-source way to raise the cost and uncertainty of AI-assisted reverse engineering, although its reported token inflation and blocking results have not been independently validated.
中大本科生反AI逆向项目火了!让黑客Token账单原地暴涨300倍 – 量子位
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
中大本科生反AI逆向项目火了!让黑客Token账单原地暴涨300倍

投毒 → 耗尽预算 → 诱导误判