@inproceedings{lekkala-etal-2025-cnlp,
title = "{CNLP}-{NITS}-{PP} at {G}en{AI} Detection Task 3: Cross-Domain Machine-Generated Text Detection Using {D}istil{BERT} Techniques",
author = "Lekkala, Sai Teja and
Yadagiri, Annepaka and
Vardhan, Mangadoddi Srikar and
Pakray, Partha",
editor = "Alam, Firoj and
Nakov, Preslav and
Habash, Nizar and
Gurevych, Iryna and
Chowdhury, Shammur and
Shelmanov, Artem and
Wang, Yuxia and
Artemova, Ekaterina and
Kutlu, Mucahid and
Mikros, George",
booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2025.genaidetect-1.38/",
pages = "334--339",
abstract = "This paper presents a Cross-domain Machine-Generated Text Detection model developed for the COLING 2025 Workshop on Detecting AI-generated Content (DAIGenC). As large language models evolve, detecting machine-generated text becomes increasingly challenging, particularly in contexts like misinformation and academic integrity. While current detectors perform well on unseen data, they remain vulnerable to adversarial strategies, including paraphrasing, homoglyphs, misspellings, synonyms, whitespace manipulations, etc. We introduce a framework to address these adversarial tactics designed to bypass detection systems by adversarial training. Our team DistilBERT-NITS detector placed 7th in the Non-Adversarial Attacks category, and Adversarial-submission-3 achieved 17th in the Adversarial Attacks category."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lekkala-etal-2025-cnlp">
<titleInfo>
<title>CNLP-NITS-PP at GenAI Detection Task 3: Cross-Domain Machine-Generated Text Detection Using DistilBERT Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Teja</namePart>
<namePart type="family">Lekkala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annepaka</namePart>
<namePart type="family">Yadagiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mangadoddi</namePart>
<namePart type="given">Srikar</namePart>
<namePart type="family">Vardhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Mikros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a Cross-domain Machine-Generated Text Detection model developed for the COLING 2025 Workshop on Detecting AI-generated Content (DAIGenC). As large language models evolve, detecting machine-generated text becomes increasingly challenging, particularly in contexts like misinformation and academic integrity. While current detectors perform well on unseen data, they remain vulnerable to adversarial strategies, including paraphrasing, homoglyphs, misspellings, synonyms, whitespace manipulations, etc. We introduce a framework to address these adversarial tactics designed to bypass detection systems by adversarial training. Our team DistilBERT-NITS detector placed 7th in the Non-Adversarial Attacks category, and Adversarial-submission-3 achieved 17th in the Adversarial Attacks category.</abstract>
<identifier type="citekey">lekkala-etal-2025-cnlp</identifier>
<location>
<url>https://aclanthology.org/2025.genaidetect-1.38/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>334</start>
<end>339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CNLP-NITS-PP at GenAI Detection Task 3: Cross-Domain Machine-Generated Text Detection Using DistilBERT Techniques
%A Lekkala, Sai Teja
%A Yadagiri, Annepaka
%A Vardhan, Mangadoddi Srikar
%A Pakray, Partha
%Y Alam, Firoj
%Y Nakov, Preslav
%Y Habash, Nizar
%Y Gurevych, Iryna
%Y Chowdhury, Shammur
%Y Shelmanov, Artem
%Y Wang, Yuxia
%Y Artemova, Ekaterina
%Y Kutlu, Mucahid
%Y Mikros, George
%S Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
%D 2025
%8 January
%I International Conference on Computational Linguistics
%C Abu Dhabi, UAE
%F lekkala-etal-2025-cnlp
%X This paper presents a Cross-domain Machine-Generated Text Detection model developed for the COLING 2025 Workshop on Detecting AI-generated Content (DAIGenC). As large language models evolve, detecting machine-generated text becomes increasingly challenging, particularly in contexts like misinformation and academic integrity. While current detectors perform well on unseen data, they remain vulnerable to adversarial strategies, including paraphrasing, homoglyphs, misspellings, synonyms, whitespace manipulations, etc. We introduce a framework to address these adversarial tactics designed to bypass detection systems by adversarial training. Our team DistilBERT-NITS detector placed 7th in the Non-Adversarial Attacks category, and Adversarial-submission-3 achieved 17th in the Adversarial Attacks category.
%U https://aclanthology.org/2025.genaidetect-1.38/
%P 334-339
Markdown (Informal)
[CNLP-NITS-PP at GenAI Detection Task 3: Cross-Domain Machine-Generated Text Detection Using DistilBERT Techniques](https://aclanthology.org/2025.genaidetect-1.38/) (Lekkala et al., GenAIDetect 2025)
ACL