Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks

• URL: http://arxiv.org/abs/2510.08605v1
• Date: Tue, 07 Oct 2025 10:09:25 GMT
• Title: Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
• Authors: Nouar Aldahoul, Yasir Zaki,
• Abstract summary: We present a multilingual, multi-agent large language model framework with retrieval-augmented generation that can be deployed as a web plugin into online platforms.<n>Our work underscores the importance of AI-driven misinformation detection in safeguarding online factual integrity against diverse attacks.
• Score: 1.3521447196536418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid spread of misinformation on digital platforms threatens public discourse, emotional stability, and decision-making. While prior work has explored various adversarial attacks in misinformation detection, the specific transformations examined in this paper have not been systematically studied. In particular, we investigate language-switching across English, French, Spanish, Arabic, Hindi, and Chinese, followed by translation. We also study query length inflation preceding summarization and structural reformatting into multiple-choice questions. In this paper, we present a multilingual, multi-agent large language model framework with retrieval-augmented generation that can be deployed as a web plugin into online platforms. Our work underscores the importance of AI-driven misinformation detection in safeguarding online factual integrity against diverse attacks, while showcasing the feasibility of plugin-based deployment for real-world web applications.

Related papers

• MultiCaption: Detecting disinformation using multilingual visual claims [10.69065586825833]
  We present MultiCaption, a dataset specifically designed for detecting contradictions in visual claims.<n>The resulting dataset comprises 11,088 visual claims in 64 languages.<n>The gains from multilingual training and testing highlight the dataset's potential for building effective multilingual fact-checking pipelines.
  arXiv  Detail & Related papers  (2026-01-16T11:57:07Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models [49.16690802656554]
  We find that Multilingual factual models struggle to provide consistent responses to semantically equivalent prompts in different languages.<n>We propose a linear shortcut method that bypasses computations in the final layers, enhancing both prediction accuracy and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-04-05T19:43:10Z)
• Entity-aware Cross-lingual Claim Detection for Automated Fact-checking [7.242609314791262]
  We introduce EX-Claim, an entity-aware cross-lingual claim detection model that generalizes well to handle multilingual claims.<n>We show consistent performance gains across 27 languages and robust knowledge transfer between languages seen and unseen during training.
  arXiv  Detail & Related papers  (2025-03-19T14:00:55Z)
• A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers [51.8203871494146]
  The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing.<n>Despite the breakthroughs of LLMs, the investigation into the multilingual scenario remains insufficient.<n>This survey aims to help the research community address multilingual problems and provide a comprehensive understanding of the core concepts, key techniques, and latest developments in multilingual natural language processing based on LLMs.
  arXiv  Detail & Related papers  (2024-05-17T17:47:39Z)
• A Roadmap for Multilingual, Multimodal Domain Independent Deception Detection [2.1506382989223782]
  Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. Recent studies have shown the possibility of the existence of universal linguistic cues to deception across domains within the English language. The practical task of deception detection in low-resource languages is not a well-studied problem due to the lack of labeled data.
  arXiv  Detail & Related papers  (2024-05-07T00:38:34Z)
• Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts [2.406214748890827]
  This paper proposes an approach to detection of online sexual predatory chats and abusive language using the open-source pretrained Llama 2 7B- parameter model. We fine-tune the LLM using datasets with different sizes, imbalance degrees, and languages (i.e., English, Roman Urdu and Urdu) Experimental results show a strong performance of the proposed approach, which performs proficiently and consistently across three distinct datasets.
  arXiv  Detail & Related papers  (2023-08-28T16:18:50Z)
• Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word Camouflage [64.78260098263489]
  Twisting and camouflaging keywords are among the most used techniques to evade platform content moderation systems. This article contributes significantly to countering malicious information by developing multilingual tools to simulate and detect new methods of evasion of content.
  arXiv  Detail & Related papers  (2022-12-27T16:08:49Z)
• Overcoming Language Disparity in Online Content Classification with Multimodal Learning [22.73281502531998]
  Large language models are now the standard to develop state-of-the-art solutions for text detection and classification tasks. The development of advanced computational techniques and resources is disproportionately focused on the English language. We explore the promise of incorporating the information contained in images via multimodal machine learning.
  arXiv  Detail & Related papers  (2022-05-19T17:56:02Z)
• BERTuit: Understanding Spanish language in Twitter through a native transformer [70.77033762320572]
  We present bfBERTuit, the larger transformer proposed so far for Spanish language, pre-trained on a massive dataset of 230M Spanish tweets. Our motivation is to provide a powerful resource to better understand Spanish Twitter and to be used on applications focused on this social network.
  arXiv  Detail & Related papers  (2022-04-07T14:28:51Z)
• A New Generation of Perspective API: Efficient Multilingual Character-level Transformers [66.9176610388952]
  We present the fundamentals behind the next version of the Perspective API from Google Jigsaw. At the heart of the approach is a single multilingual token-free Charformer model. We demonstrate that by forgoing static vocabularies, we gain flexibility across a variety of settings.
  arXiv  Detail & Related papers  (2022-02-22T20:55:31Z)

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.