Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction

TL;DR

This paper introduces a zero-shot detection framework using multiscaled conformal prediction to reliably bound false positives in machine-generated text detection, improving accuracy and robustness.

Contribution

It proposes a novel MCP framework that constrains false positive rates while enhancing detection performance, along with a new diverse dataset, RealDet.

Findings

MCP effectively constrains false positive rates.

Detection performance is significantly improved.

Robustness against adversarial attacks is increased.

Abstract

The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors. As a result, developing effective detectors to mitigate these risks has become a critical priority. However, most existing detection methods focus excessively on detection accuracy, often neglecting the societal risks posed by high false positive rates (FPRs). This paper addresses this issue by leveraging Conformal Prediction (CP), which effectively constrains the upper bound of FPRs. While directly applying CP constrains FPRs, it also leads to a significant reduction in detection performance. To overcome this trade-off, this paper proposes a Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction (MCP), which both enforces the FPR constraint and improves detection performance. This paper also introduces RealDet, a high-quality dataset that spans a wide range of domains, ensuring realistic calibration and enabling superior detection performance when combined with MCP. Empirical evaluations demonstrate that MCP effectively constrains FPRs, significantly enhances detection performance, and increases robustness against adversarial attacks across multiple detectors and datasets.