RECORD
A Machine Learning Approach To Prevent Malicious Calls Over Telephony Networks
Cryptography and Security · Submitted 7 Apr 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We extensively evaluate different state-of-the-art machine learning approaches using the proposed features, and the results show that the best approach can reduce up to 90% unblocked malicious calls while maintaining a precision over 99.99% on the benign call traffic.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Malicious calls, i.e., telephony spams and scams, have been a long-standing challenging issue that causes billions of dollars of annual financial loss worldwide. This work presents the first machine learning-based solution without relying on any particular assumptions on the underlying telephony network infrastructures. The main challenge of this decade-long problem is that it is unclear how to construct effective features without the access to the telephony networks' infrastructures. We solve this problem by combining several innovations. We first develop a TouchPal user interface on top of a mobile App to allow users tagging malicious calls. This allows us to maintain a large-scale call log database. We then conduct a measurement study over three months of call logs, including 9 billion records. We design 29 features based on the results, so that machine learning algorithms can be used to predict malicious calls. We extensively evaluate different state-of-the-art machine learning approaches using the proposed features, and the results show that the best approach can reduce up to 90% unblocked malicious calls while maintaining a precision over 99.99% on the benign call traffic. The results also show the models are efficient to implement without incurring a significant latency overhead. We also conduct ablation analysis, which reveals that using 10 out of the 29 features can reach a performance comparable to using all features.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Malicious calls, i.e., telephony spams and scams, have been a long-standing challenging issue that causes billions of dollars of annual financial loss worldwide. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | This work presents the first machine learning-based solution without relying on any particular assumptions on the underlying telephony network infrastructures. | contribution 1.00 | 0.90 | 0.12 | asserted 1.00 |
| s2 | The main challenge of this decade-long problem is that it is unclear how to construct effective features without the access to the telephony networks' infrastructures. | gap 0.97 | 0.08 | 0.02 | asserted 0.98 |
| s3 | We solve this problem by combining several innovations. | contribution 0.62 | 0.79 | 0.03 | asserted 0.97 |
| s4 | We first develop a TouchPal user interface on top of a mobile App to allow users tagging malicious calls. | method 0.94 | 0.96 | 0.02 | asserted 1.00 |
| s5 | This allows us to maintain a large-scale call log database. | method 0.86 | 0.86 | 0.02 | asserted 0.94 |
| s6 | We then conduct a measurement study over three months of call logs, including 9 billion records. | method 0.96 | 0.97 | 0.02 | asserted 1.00 |
| s7 | We design 29 features based on the results, so that machine learning algorithms can be used to predict malicious calls. | method 0.96 | 0.97 | 0.05 | asserted 0.99 |
| s8 | We extensively evaluate different state-of-the-art machine learning approaches using the proposed features, and the results show that the best approach can reduce up to 90% unblocked malicious calls while maintaining a precision over 99.99% on the benign call traffic. | result 1.00 | 0.97 | 0.83 | asserted 1.00 |
| s9 | The results also show the models are efficient to implement without incurring a significant latency overhead. | result 1.00 | 0.94 | 0.08 | asserted 1.00 |
| s10 | We also conduct ablation analysis, which reveals that using 10 out of the 29 features can reach a performance comparable to using all features. | result 0.95 | 0.98 | 0.06 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Malicious calls, i.e., telephony spams and scams, have been a long-standing challenging issue that causes billions of dollars of annual financial loss worldwide. This work presents the first machine learning-based solution without relying on any particular assumptions on the underlying telephony network infrastructures. The main challenge of this decade-long problem is that it is unclear how to construct effective features without the access to the telephony networks' infrastructures. We solve this problem by combining several innovations. We first develop a TouchPal user interface on top of a mobile App to allow users tagging malicious calls. This allows us to maintain a large-scale call log database. We then conduct a measurement study over three months of call logs, including 9 billion records. We design 29 features based on the results, so that machine learning algorithms can be used to predict malicious calls. We extensively evaluate different state-of-the-art machine learning approaches using the proposed features, and the results show that the best approach can reduce up to 90% unblocked malicious calls while maintaining a precision over 99.99% on the benign call traffic. The results also show the models are efficient to implement without incurring a significant latency overhead. We also conduct ablation analysis, which reveals that using 10 out of the 29 features can reach a performance comparable to using all features.
Human review
How the literature uses it
1 arXiv paper cite this in 2 sentences
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.