Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910918178242560 |
|---|---|
| author | Alghuried, Ahod Alkinoon, Ali Alghamdi, Abdulaziz Choi, Soohyeon Mohaisen, Manar Mohaisen, David |
| author_facet | Alghuried, Ahod Alkinoon, Ali Alghamdi, Abdulaziz Choi, Soohyeon Mohaisen, Manar Mohaisen, David |
| contents | This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance metrics. Our findings, highlighting how prone those techniques are to simple attacks, are alarming, and the inconsistency in the attacks' effect on different algorithms promises ways for attack mitigation. We examine the effectiveness of different mitigation strategies, including adversarial training and enhanced feature selection, in enhancing model robustness and show their effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations Alghuried, Ahod Alkinoon, Ali Alghamdi, Abdulaziz Choi, Soohyeon Mohaisen, Manar Mohaisen, David Cryptography and Security This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance metrics. Our findings, highlighting how prone those techniques are to simple attacks, are alarming, and the inconsistency in the attacks' effect on different algorithms promises ways for attack mitigation. We examine the effectiveness of different mitigation strategies, including adversarial training and enhanced feature selection, in enhancing model robustness and show their effectiveness. |
| title | Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2504.17684 |