Beyond The Surface: Characterizing Adversarial Boundaries in Synthetic Text Attribution Across Heterogeneous Domains

Anita Rani and Suman

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2026, vol. 12, issue 4, 87-100

Abstract: The influx of large language models (LLMs), like GPT-4, Claude, and Llama, has made distinguishing between natural and artificial content more difficult. The existing detection algorithms have three inherent drawback: they have limited ability to detect on short sentence-length texts containing less than 60 words, they are domain-specific, and they are fragile to adversarial attacks that involve synonym-replacement and paraphrasing. To overcome all three limitations, this paper proposes a hybrid detection framework which combines semantically deep embeddings from the RoBERTa transformer with a set of carefully designed language statistics (vocabulary richness, burstiness, and information entropy) and linguistic statistics (part-of-speech distributions, Flesch Reading Ease scores). The feature vector of the resulting embedding a 778-dimensional vector is handed to an ensemble of gradient-boosting trees, specifically XGBoost. The experiments are carried out on a processed database of 27,333 essays from professional, technical and social media writing, that is written by students and generated by AI tools. The proposed model is able to classify 99.00%, with an F1-score of 0.9932 and an area under the ROC curve (AUC) of 1.0. The framework achieves a 99.67% accuracy rate for perfect precision and recall for AI-generated content in the presence of synonym-based adversarial paraphrasing, showing excellent resistance to the surface-level adversarial paraphrasing strategy. Near-perfect cross-domain generalization is demonstrated and inference latency is 0.351ms per sample on average, which makes them suitable for realtime applications. These findings pave the way for scalable, accurate, adversarial-resilient AI-generated text detection using hybrid feature fusion, a paradigm that is encouraged by the results presented herein.

Keywords: AI-generated text detection; large language models; RoBERTa; XGBoost; adversarial robustness; feature fusion; natural language processing (search for similar items in EconPapers)
Date: 2026
Note: Article URL: https://ijsrcseit.com/home/article/view/CSEIT2612410
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/home/article/view/CSEIT2612410 Article URL (text/html)
https://ijsrcseit.com/home/article/download/CSEIT2612410/CSEIT2612410 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v12:y2026:i4:id:2115

DOI: 10.32628/CSEIT2612410

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma (USA) ().