Enforcing Cybersecurity Constraints for LLM-driven Robot Agents for Online Transactions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908298237706240 |
|---|---|
| author | Shah, Shraddha Pradipbhai Deshpande, Aditya Vilas |
| author_facet | Shah, Shraddha Pradipbhai Deshpande, Aditya Vilas |
| contents | The integration of Large Language Models (LLMs) into autonomous robotic agents for conducting online transactions poses significant cybersecurity challenges. This study aims to enforce robust cybersecurity constraints to mitigate the risks associated with data breaches, transaction fraud, and system manipulation. The background focuses on the rise of LLM-driven robotic systems in e-commerce, finance, and service industries, alongside the vulnerabilities they introduce. A novel security architecture combining blockchain technology with multi-factor authentication (MFA) and real-time anomaly detection was implemented to safeguard transactions. Key performance metrics such as transaction integrity, response time, and breach detection accuracy were evaluated, showing improved security and system performance. The results highlight that the proposed architecture reduced fraudulent transactions by 90%, improved breach detection accuracy to 98%, and ensured secure transaction validation within a latency of 0.05 seconds. These findings emphasize the importance of cybersecurity in the deployment of LLM-driven robotic systems and suggest a framework adaptable to various online platforms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15546 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enforcing Cybersecurity Constraints for LLM-driven Robot Agents for Online Transactions Shah, Shraddha Pradipbhai Deshpande, Aditya Vilas Cryptography and Security Artificial Intelligence Computers and Society The integration of Large Language Models (LLMs) into autonomous robotic agents for conducting online transactions poses significant cybersecurity challenges. This study aims to enforce robust cybersecurity constraints to mitigate the risks associated with data breaches, transaction fraud, and system manipulation. The background focuses on the rise of LLM-driven robotic systems in e-commerce, finance, and service industries, alongside the vulnerabilities they introduce. A novel security architecture combining blockchain technology with multi-factor authentication (MFA) and real-time anomaly detection was implemented to safeguard transactions. Key performance metrics such as transaction integrity, response time, and breach detection accuracy were evaluated, showing improved security and system performance. The results highlight that the proposed architecture reduced fraudulent transactions by 90%, improved breach detection accuracy to 98%, and ensured secure transaction validation within a latency of 0.05 seconds. These findings emphasize the importance of cybersecurity in the deployment of LLM-driven robotic systems and suggest a framework adaptable to various online platforms. |
| title | Enforcing Cybersecurity Constraints for LLM-driven Robot Agents for Online Transactions |
| topic | Cryptography and Security Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2503.15546 |