# Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

arXiv: https://arxiv.org/abs/2406.01179 · HTML: https://mlsanity.com/paper/2406.01179/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [MGTBench: Benchmarking Machine-Generated Text Detection](https://mlsanity.com/paper/2303.14822/) (2023)
- [Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method](https://mlsanity.com/paper/2305.13412/) (2023)
- [Do We Need Zero Training Loss After Achieving Zero Training Error?](https://mlsanity.com/paper/2002.08709/) (2020)
- [Certified Robustness to Text Adversarial Attacks by Randomized [MASK]](https://mlsanity.com/paper/2105.03743/) (2021)
- [SeqXGPT: Sentence-Level AI-Generated Text Detection](https://mlsanity.com/paper/2310.08903/) (2023)
- [Few-Shot Detection of Machine-Generated Text using Style Representations](https://mlsanity.com/paper/2401.06712/) (2024)

## Built on by (most cited first, 16 of 16)

- [DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution](https://mlsanity.com/paper/2512.04838/) (2025)
- [Beyond Easy Wins: A Text Hardness-Aware Benchmark for LLM-generated Text Detection](https://mlsanity.com/paper/2507.15286/) (2025)
- [Explainability-Based Token Replacement on LLM-Generated Text](https://mlsanity.com/paper/2506.04050/) (2025)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations](https://mlsanity.com/paper/2504.21019/) (2025)
- [Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection](https://mlsanity.com/paper/2406.16275/) (2024)
- [Discourse Features Enhance Detection of Document-Level Machine-Generated Content](https://mlsanity.com/paper/2412.12679/) (2024)
- [Could AI Trace and Explain the Origins of AI-Generated Images and Text?](https://mlsanity.com/paper/2504.04279/) (2025)
- [Complete Evasion, Zero Modification: PDF Attacks on AI Text Detection](https://mlsanity.com/paper/2508.01887/) (2025)
- [MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark](https://mlsanity.com/paper/2601.04633/) (2026)
- [Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection](https://mlsanity.com/paper/2604.13692/) (2026)
- [Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization](https://mlsanity.com/paper/2606.00392/) (2026)
- [A Mathematical Theory of Discursive Networks](https://mlsanity.com/paper/2507.06565/) (2025)
- [The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence](https://mlsanity.com/paper/2606.07916/) (2026)
- [SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents](https://mlsanity.com/paper/2606.18946/) (2026)
- [T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting](https://mlsanity.com/paper/2607.14113/) (2026)

## Abstract (arXiv)

The widespread use of large language models (LLMs) has sparked concerns about the potential misuse of AI-generated text, as these models can produce content that closely resembles human-generated text. Current detectors for AI-generated text (AIGT) lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text. This paper investigates the robustness of existing AIGT detection methods and introduces a novel detector, the Siamese Calibrated Reconstruction Network (SCRN). The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations. We also propose a siamese calibration technique to train the model to make equally confidence predictions under different noise, which improves the model's robustness against adversarial perturbations. Experiments on four publicly available datasets show that the SCRN outperforms all baseline methods, achieving 6.5%-18.25% absolute accuracy improvement over the best baseline method under adversarial attacks. Moreover, it exhibits superior generalizability in cross-domain, cross-genre, and mixed-source scenarios. The code is available at urlhttps://github.com/CarlanLark/Robust-AIGC-Detector.