Image classifiers reportedly bypassable via artistic style descriptions
AI summary
X user @MinLiBuilds said that image classifiers increase defenses when encountering certain body-related descriptions, but the classifier can be bypassed after describing the content as marble sculptures, classical oil paintings, single-line drawings, or cyberpunk and other artistic styles.
Full text · Original
✍️ 图片破甲的原理, 当你出现搞、“巨大、扔子、福,罩杯,分类器的防御值就拉满了。
但是如果你描述成艺术品,比如大理石雕塑、古典油画、单线线描、甚至赛博朋克。
破甲开始了。
一通百通 👇
https://x.com/i/article/2104211268307460096View the quoted post on X