Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910111882018816 |
|---|---|
| author | Kassa, Yonas Bonacci, James Wang, Ping |
| author_facet | Kassa, Yonas Bonacci, James Wang, Ping |
| contents | The transformative potential of large language models (LLMs) in education, such as improving accessibility and personalized learning, is being eclipsed by significant challenges. These challenges stem from concerns that LLMs undermine academic assessment by enabling bypassing of critical thinking, leading to increased cognitive offloading. This emerging trend stresses the dual imperative of harnessing AI's educational benefits while safeguarding critical thinking and academic rigor in the evolving AI ecosystem. To this end, we introduce AI-Sinkhole, an AI-agent augmented DNS-based framework that dynamically discovers, semantically classifies, and temporarily network-wide blocks emerging LLM chatbot services during proctored exams. AI-Sinkhole offers explainable classification via quantized LLMs (LLama 3, DeepSeek-R1, Qwen-3) and dynamic DNS blocking with Pi-Hole. We also share our observations in using LLMs as explainable classifiers which achieved robust cross-lingual performance (F1-score > 0.83). To support future research and development in this domain initial codes with a readily deployable 'AI-Sinkhole' blockist is available on https://github.com/AIMLEdu/ai-sinkhole. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02360 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations Kassa, Yonas Bonacci, James Wang, Ping Networking and Internet Architecture Artificial Intelligence Computers and Society Emerging Technologies Machine Learning 68T05 I.2.1 The transformative potential of large language models (LLMs) in education, such as improving accessibility and personalized learning, is being eclipsed by significant challenges. These challenges stem from concerns that LLMs undermine academic assessment by enabling bypassing of critical thinking, leading to increased cognitive offloading. This emerging trend stresses the dual imperative of harnessing AI's educational benefits while safeguarding critical thinking and academic rigor in the evolving AI ecosystem. To this end, we introduce AI-Sinkhole, an AI-agent augmented DNS-based framework that dynamically discovers, semantically classifies, and temporarily network-wide blocks emerging LLM chatbot services during proctored exams. AI-Sinkhole offers explainable classification via quantized LLMs (LLama 3, DeepSeek-R1, Qwen-3) and dynamic DNS blocking with Pi-Hole. We also share our observations in using LLMs as explainable classifiers which achieved robust cross-lingual performance (F1-score > 0.83). To support future research and development in this domain initial codes with a readily deployable 'AI-Sinkhole' blockist is available on https://github.com/AIMLEdu/ai-sinkhole. |
| title | Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations |
| topic | Networking and Internet Architecture Artificial Intelligence Computers and Society Emerging Technologies Machine Learning 68T05 I.2.1 |
| url | https://arxiv.org/abs/2604.02360 |