EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
Social media has become integral to minors' daily lives and is used for various purposes, such as making friends, exploring shared interests, and engaging in educational activities. However, the increase in screen time has also led to heightened challenges, including cyberbullying, online grooming, and exploitations posed by malicious actors. Traditional content moderation techniques have proven ineffective against exploiters' evolving tactics. To address these growing challenges, we propose the EdgeAIGuard content moderation approach that is designed to protect minors from online grooming and various forms of digital exploitation. The proposed method comprises a multi-agent architecture deployed strategically at the network edge to enable rapid detection with low latency and prevent harmful content targeting minors. The experimental results show the proposed method is significantly more effective than the existing approaches.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 16 of its 48 references that are in the map. First posted on arXiv 28 Feb 2025.
Builds on
16 of 48 references.
References · 16
- 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 736
- 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
- 2017Deep Learning for Hate Speech Detection in Tweetscited by 180
- 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
- 2023Evaluating GPT-3 Generated Explanations for Hateful Content Moderationcited by 46
- 2023ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Reviewcited by 28
- 2021A systematic review of Hate Speech automatic detection using Natural Language Processingcited by 27
- 2021Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Modelcited by 26
- 2018Challenges in Discriminating Profanity from Hate Speechcited by 23
- 2020Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERTcited by 19
- 2018Hate Speech Detection from Code-mixed Hindi-English Tweets Using Deep Learning Modelscited by 16
- 2024Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationalescited by 16
4 more
- 2024Legilimens: Practical and Unified Content Moderation for Large Language Model Servicescited by 13
- 2023ChatGPT in the Age of Generative AI and Large Language Models: A Concise Surveycited by 10
- 2024HateTinyLLM : Hate Speech Detection Using Tiny Large Language Modelscited by 7
- 2023TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysiscited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
- 2026On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer Fingerprinting
- 2025MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media
- 2024TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System
- 2026Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue
- 2025Agent Guide: A Simple Agent Behavioral Watermarking Framework
- 2026When Agents Talk: Discourse, Manipulation, and Risk in an Agentic Social Network
- 2024Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance