An LLM-based Chain-of-Response Counter-Scam System
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918534447104000 |
|---|---|
| author | Kim, Heedou Gim, Mogan Choi, Donghee Lee, Hoonick Bae, Soonil Kim, Mi-Young Kang, Jaewoo |
| author_facet | Kim, Heedou Gim, Mogan Choi, Donghee Lee, Hoonick Bae, Soonil Kim, Mi-Young Kang, Jaewoo |
| contents | The rapid evolution of online scams, driven by transnational networks and mass produced social engineering scenarios, has exposed the speed limitations of conventional detection, necessitating tighter interagency coordination. While LLMs show promise in scam identification, their role in accelerating integrated response frameworks remains underexplored. We propose Counter Scam, a unified LLM based multiagent framework that orchestrates end to end response from initial detection to crime investigation. The framework first proposes safe data guidelines, emphasizing nonpublic scam data and secure dataset construction via scam specific NER. Developed with insights from 37 stakeholders to reduce delays and improve analytical efficiency, the system integrates CSRA for multiagent mitigation, CSRT comprising nine role aligned NLP tasks, and CSRD, a corpus of 185,300 scam cases and 38,587 knowledge entries. Experiments show that fine tuned sLLMs surpass commercial models by more than 10% across all CSRT tasks and achieve a 0.24 F1 improvement in scam specific NER. These results demonstrate the framework's capability to enable rapid and collaborative mitigation of online scams. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01475 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An LLM-based Chain-of-Response Counter-Scam System Kim, Heedou Gim, Mogan Choi, Donghee Lee, Hoonick Bae, Soonil Kim, Mi-Young Kang, Jaewoo Computers and Society The rapid evolution of online scams, driven by transnational networks and mass produced social engineering scenarios, has exposed the speed limitations of conventional detection, necessitating tighter interagency coordination. While LLMs show promise in scam identification, their role in accelerating integrated response frameworks remains underexplored. We propose Counter Scam, a unified LLM based multiagent framework that orchestrates end to end response from initial detection to crime investigation. The framework first proposes safe data guidelines, emphasizing nonpublic scam data and secure dataset construction via scam specific NER. Developed with insights from 37 stakeholders to reduce delays and improve analytical efficiency, the system integrates CSRA for multiagent mitigation, CSRT comprising nine role aligned NLP tasks, and CSRD, a corpus of 185,300 scam cases and 38,587 knowledge entries. Experiments show that fine tuned sLLMs surpass commercial models by more than 10% across all CSRT tasks and achieve a 0.24 F1 improvement in scam specific NER. These results demonstrate the framework's capability to enable rapid and collaborative mitigation of online scams. |
| title | An LLM-based Chain-of-Response Counter-Scam System |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2606.01475 |