3

I am conducting researches into a voice phishing attacks/scam phone call detection system using machine learning. However, I am facing difficulties to find an open dataset of voice phishing or phone calls logs I could work with.

Please, can anyone guide me to any related dataset? Or even suggestion on how to create such a dataset and deal with voice phishing?

Any opinions are welcome.

Thank you.

1

I think you are referring to voice spoofing, which can be part of the phishing process. In the context of voice, the term spoofing is more common in literature. Spoofing/ phishing can take various forms either by using a replayed audio (if only a password is required for example) or an advanced voice synthesis/cloning system etc. Therefore the datasets can differ in their structure depending on the research specifications. The following are some datasets used in anti-spoofing research:

| improve this answer | |
  • 1
    Hello, Thank you for your reply. Actually, the type of dataset I was looking for was the call detail record (CDR) enabling the program to detect if a call is genuine or a scam. After check around it turned out that they are really difficult to get from Telecom operator because of privacy concerns. So I had to find an alternative for the project. I will use the given link about spoofing for further research. Thank you. – Milandu Keith Jul 16 at 7:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.