Adversarial Creation and Detection of AI-Generated Social Bot Content

• URL: http://arxiv.org/abs/2606.07219v1
• Date: Fri, 05 Jun 2026 12:32:47 GMT
• Title: Adversarial Creation and Detection of AI-Generated Social Bot Content
• Abstract summary: Existing models for detecting AI-generated content often fail in the wild, primarily due to the lack of ground-truth data.<n>We address this gap through an adversarial methodology that models the impersonation of real social media users by malicious actors.<n>Our approach significantly outperforms existing models for content-based bot detection in real-world, out-of-distribution data.
• Score: 48.21614389337061
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The convergence of large language models and social bots allows malicious actors to manipulate the information ecosystem by generating human-like content at scale. Existing models for detecting AI-generated content often fail in the wild, primarily due to the lack of ground-truth data. We address this gap through an adversarial methodology that models the impersonation of real social media users by malicious actors. Using this methodology, we curate a multilingual, cross-platform dataset of paired human and AI-generated messages. Training on such adversarial data yields accurate detection of AI-generated text. Our approach significantly outperforms existing models for content-based bot detection in real-world, out-of-distribution data.

Related papers

• Detecting AI-Generated Content on Social Media with Multi-modal Language Models [47.35729326899949]
  Existing AI-generated content (AIGC) detection methods face challenges including poor generalization to new generation models.<n>We present our pipeline that mitigates these issues by curating diverse multi-modal social media data.<n>Our model achieves state-of-the-art detection performance on public benchmarks and demonstrates robust detection and explanation capabilities.
  arXiv  Detail & Related papers  (2026-04-21T20:05:02Z)
• FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation [52.56850762009136]
  Social bot detection is critical to the stability and security of online social platforms.<n>Current state-of-the-art bot detection models are largely developed in isolation.<n>We propose FedRio as a cross-platform and cross-model detection framework.
  arXiv  Detail & Related papers  (2026-04-12T15:13:41Z)
• TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns [7.648264389927362]
  Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse.<n>Existing methods suffer from limited detection accuracy due to overreliance on single-modality signals.<n>We propose TRACE-Bot, a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns.
  arXiv  Detail & Related papers  (2026-04-02T15:16:14Z)
• ChatGpt Content detection: A new approach using xlm-roberta alignment [0.0]
  We present a comprehensive methodology to detect AI-generated text using XLM-RoBERTa, a state-of-the-art multilingual transformer model.<n>We fine-tuned the model on a balanced dataset of human and AI-generated texts and evaluated its performance.<n>Our findings offer a valuable tool for maintaining academic integrity and contribute to the broader field of AI ethics.
  arXiv  Detail & Related papers  (2025-11-26T03:16:57Z)
• RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction [51.46634975923564]
  This paper proposes the first adversarial multi-agent Reinforcement learning framework for social Bot control attacks (RoBCtrl)<n> Specifically, we use a diffusion model to generate high-fidelity bot accounts by reconstructing existing account data with minor modifications.<n>We then employ a Multi-Agent Reinforcement Learning (MARL) method to simulate bots adversarial behavior.
  arXiv  Detail & Related papers  (2025-10-16T02:41:49Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• BotTrans: A Multi-Source Graph Domain Adaptation Approach for Social Bot Detection [55.31623652907614]
  We propose a multi-source graph domain adaptation model named textitBotTrans for detecting social bots.<n>We first leverage the labeling knowledge shared across multiple source networks to establish a cross-source-domain topology.<n>We then aggregate cross-domain neighbor information to enhance the discriminability of source node embeddings.
  arXiv  Detail & Related papers  (2025-06-12T02:10:36Z)
• When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text [13.14749943120523]
  Social media represents a significant attack vector in online influence campaigns.<n>We create a dataset of 505,159 AI-generated social media posts from a combination of open-source, closed-source, and fine-tuned LLMs.<n>We show that while the posts can be detected under typical research assumptions, under the more realistic assumption that an attacker will not release their fine-tuned model to the public, detectability drops dramatically.
  arXiv  Detail & Related papers  (2025-06-11T17:51:28Z)
• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  This study systematically evaluations twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset.<n>Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• Who Said That? Benchmarking Social Media AI Detection [12.862865254507177]
  This paper introduces SAID (Social media AI Detection), a novel benchmark developed to assess AI-text detection models' capabilities in real social media platforms. It incorporates real AI-generate text from popular social media platforms like Zhihu and Quora. A notable finding of our study, based on the Zhihu dataset, reveals that annotators can distinguish between AI-generated and human-generated texts with an average accuracy rate of 96.5%.
  arXiv  Detail & Related papers  (2023-10-12T11:35:24Z)
• Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions [9.578008322407928]
  Language generation models' democratization makes it easier to generate human-like text at-scale for nefarious activities. It is essential to understand how people interact with bots and develop methods to detect bot-generated text. This paper shows that bot-generated text detection methods are more robust across datasets and models if we use information about how people respond to it.
  arXiv  Detail & Related papers  (2021-06-02T14:10:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.