Review

The adversarial game between detection and evasion: A survey of anti-detection techniques for machine-generated texts.

De-Yu Meng Tad Gonsalves

Sep 2026 · Neural Networks · Vol 205 Pt C, pp. 109562 · 0 citations · 47 references

Medicine

TL;DR

This paper systematically synthesizes 27 studies of attacks against MGTD and the available evidence on corresponding defenses, categorizing existing research into four major types of evasion strategies: watermark attacks, paraphrasing attacks, prompt-based attacks, and adversarial-text attacks, and summarizes the available defense evidence.

Abstract

With the explosive growth of large language models (LLMs), research on machine-generated text detection (MGTD) has also proliferated. Alongside these developments, a wide range of attack algorithms targeting MGTD systems have emerged. While previous studies have surveyed detection techniques, few have examined the dynamic interplay between attack and defense. Following PRISMA 2020, this paper systematically synthesizes 27 studies of attacks against MGTD and the available evidence on corresponding defenses. We categorize existing research into four major types of evasion strategies: watermark attacks, paraphrasing attacks, prompt-based attacks, and adversarial-text attacks, and summarize the available defense evidence. Furthermore, to better understand the practical implications of these methods, we compile the reported performance results of attack and defense techniques across different detectors. Finally, we highlight the current challenges in this area and outline potential future research directions. A companion repository containing the categorized literature, paper links, and available code, data, and project repositories is provided at https://github.com/AIGC1999/A-Survey-of-Anti-Detection-Techniques-for-Machine-Generated-Texts.

DOI PubMed Semantic Scholar

View source

Similar papers

Preprint Sep 2026

Breaking Windows Malware Detection: A Comprehensive Evaluation of Problem-Space Adversarial Robustness

Problem-space evasion attacks have exposed critical weaknesses in machine learning-based malware detectors; yet, their evaluation remains fragmented across models, datasets, and attack methodologies, often neglecting domain-specific requirements such as executability and functionality preservation. We address this gap...

Mashal Zainab, Salijona Dyrmishi, Hamid Bostani et al. · 0 citations

Preprint Sep 2026

Robustness Evaluation and Detection of Transferable Adversarial Attacks in ML-Based NIDS

Machine learning-based network intrusion detection systems (ML-based NIDS) are vulnerable to adversarial evasion, where malicious samples are perturbed to evade detection and be misclassified as benign. Despite growing research on adversarial attacks and defenses for ML-based NIDS, comparative evaluations of multiple a...

Huda Ali Alatawi · 0 citations

#artificial intelligence Preprint Sep 2026

Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

Two universal tool-based defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning.

Xiao-Yan Li, Yun-Li Wang · 0 citations

Preprint Aug 2026

Adversarial Robustness in Smishing Detection: A Comparative Analysis of Adversarial Fragility in Classical vs. Transformer-Based Detection Systems

It is demonstrated that clean-text performance is not a reliable predictor of adversarial robustness, and the results underscore the necessity for architecture-specific defences and frame smishing detection as an adversarial cybersecurity challenge rather than a static classification task.

Denzel Chiuseni, A. Bahizire, Silva Hama et al. · 0 citations

Open access Dec 2025

AI security beyond core domains: resume screening as a case study of adversarial vulnerabilities in specialized LLM applications

A benchmark for this vulnerability in LLM-based resume screening is introduced: 463 job-candidate pairs drawn from a 14-domain corpus, with the evaluated sample covering 13 domains, attacked through a taxonomy of four attack types and four injection positions.

Hong-Lin Mu, Jinghao Liu, Kai-Yang Wan et al. · International Journal of Mac... · 4 citations · ⚡1

Open access Aug 2026

Breaking and Defending LLM-Powered Social Media Bot Detection Systems †

The solution, LSABRE, is a multi-LLM framework that improves robustness across various attacks, maintaining 86% detection accuracy even under strong adaptive adversarial attacks, and proposes a robust multi-LLM defense architecture designed to preserve detection reliability under adaptive adversarial conditions.

Nof Orenstein, Yoni Birman · Pragmatic Cybersecurity · 0 citations