Authorship attribution in the era of llms: Problems, methodologies, and challenges

B Huang, C Chen, K Shu - ACM SIGKDD Explorations Newsletter, 2025 - dl.acm.org
Accurate attribution of authorship is crucial for maintaining the integrity of digital content,
improving forensic investigations, and mitigating the risks of misinformation and plagiarism …

GenAI Content Detection Task 2: AI vs. Human--Academic Essay Authenticity Challenge

SA Chowdhury, H Almerekhi, M Kutlu, KE Keles… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper presents a comprehensive overview of the first edition of the Academic Essay
Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks …

Large Model Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends

Y Wang, Y Pan, Q Zhao, Y Deng, Z Su, L Du… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Model (LM) agents, powered by large foundation models such as GPT-4 and DALL-E
2, represent a significant step towards achieving Artificial General Intelligence (AGI). LM …

Defending mutation-based adversarial text perturbation: a black-box approach

D Deanda, I Alsmadi, J Guerrero, G Liang - Cluster Computing, 2025 - Springer
The proliferation of text generation applications in social networks has raised concerns
about the authenticity of online content. Large language models like GPTs can now produce …

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection

P Miralles-González, J Huertas-Tato, A Martín… - arxiv preprint arxiv …, 2025 - arxiv.org
The rapid advancement in large language models (LLMs) has significantly enhanced their
ability to generate coherent and contextually relevant text, raising concerns about the …

MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts

D Macko, J Kopal, R Moro, I Srba - arxiv preprint arxiv:2406.12549, 2024 - arxiv.org
Recent LLMs are able to generate high-quality multilingual texts, indistinguishable for
humans from authentic human-written ones. Research in machine-generated text detection …

Beemo: Benchmark of Expert-edited Machine-generated Outputs

E Artemova, J Lucas, S Venkatraman, J Lee… - arxiv preprint arxiv …, 2024 - arxiv.org
The rapid proliferation of large language models (LLMs) has increased the volume of
machine-generated texts (MGTs) and blurred text authorship in various domains. However …

DAMAGE: Detecting Adversarially Modified AI Generated Text

E Masrour, B Emi, M Spero - arxiv preprint arxiv:2501.03437, 2025 - arxiv.org
AI humanizers are a new class of online software tools meant to paraphrase and rewrite AI-
generated text in a way that allows them to evade AI detection software. We study 19 AI …

Zero-Shot Machine-Generated Text Detection Using Mixture of Large Language Models

M Dubois, F Yvon, P Piantanida - arxiv preprint arxiv:2409.07615, 2024 - arxiv.org
The dissemination of Large Language Models (LLMs), trained at scale, and endowed with
powerful text-generating abilities has vastly increased the threats posed by generative AI …

LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts

HDS Gameiro, A Kucharavy, L Dolamic - arxiv preprint arxiv:2409.03291, 2024 - arxiv.org
With the emergence of widely available powerful LLMs, disinformation generated by large
Language Models (LLMs) has become a major concern. Historically, LLM detectors have …