Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
Year: 2026
Type: conference-paper
Abstract: Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often fail under limited fresh supervision and humanization-oriented attacks.We study this problem as few-shot robustness recovery under evolving generators, domains, and attack patterns, and use threat modeling to diagnose detector failures from an attacker's viewpoint.We identify unstable local boundary estimation as a key failure mode: under scarce supervision, humanized MGT can induce prediction flips, logit drift, and clean-adversarial representation misalignment.To address this issue, we propose RAG-GuidEd Attacker Strengthens ConTrastive Few-shot Detector (REACT), a threat-aware few-shot robustness framework.REACT uses a dynamic retrieval-guided attacker to generate boundary-oriented humanized rewrites from extreme positive-negative anchors, and trains the detector with a pairwise boundary contrastive objective to stabilize clean-adversarial local geometry.Alternating attacker-detector updates further form a co-evolutionary curriculum.Experiments on 4 datasets with 4 shot sizes and 3 random seeds show that REACT improves average detection F1 by 4.95 points over 8 SOTA detectors and reduces average attack success rate under 4 strong attacks by 3.66 percentage points.
Authors: Wenjing Duan, Qi Zhou, Yuanfan Li
Institution: Xi'an Jiaotong University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7160334591