{
  "annotation_id": "a152d498-6670-4081-9c86-9b2ea961fa51",
  "date_created": "2026-02-17T05:53:15.645000Z",
  "date_modified": "2026-02-17T05:53:15.645000Z",
  "file_hash": "78e2131741ff7d811b0b66233e3048ba47c7764a5182e0960141df6af042fdde",
  "private": false,
  "record": {
    "abstract": "The increasing misuse of AI-generated texts (AIGT) has motivated the rapid development of AIGT detection methods. However, the reliability of these detectors remains fragile against adversarial evasions. Existing attack strategies often rely on white-box assumptions or demand prohibitively high computational and interaction costs, rendering them ineffective under practical black-box scenarios. In this paper, we propose Multi-stage Alignment for Style Humanization (MASH), a novel framework that evades black-box detectors based on style transfer. MASH sequentially employs style-injection supervised fine-tuning, direct preference optimization, and inference-time refinement to shape the distributions of AI-generated texts to resemble those of human-written texts. Experiments across 6 datasets and 5 detectors demonstrate the superior performance of MASH over 11 baseline evaders. Specifically, MASH achieves an average Attack Success Rate (ASR) of 92%, surpassing the strongest baselines by an average of 24%, while maintaining superior linguistic quality.",
    "arxiv_id": "2601.08564",
    "authors": [
      "Yongtong Gu",
      "Songze Li",
      "Xia Hu"
    ],
    "categories": [
      "cs.CR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization",
    "url": "https://arxiv.org/abs/2601.08564",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "ba996cf0-bb33-4001-891b-bc242d5b38e9",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}