Presentation Material

Abstract

Anytime you want to bypass the system, you tend to have a telephone conversation instead of leaving a paper trail. Data Leakage Prevention (DLP) is on top of the list for most organizations, be it financial or medical industry. In order to overcome this issue we need to devise a new system that can monitor phone conversations. Voice Data Leakage Detection System can be used for tracking Credit card, social security numbers, along with other PII data. An extension of this can be used for tracking Accounting and Financial information that leaves the organization before the information is actually public. This will help spot the people leaking insider information to traders, competitors and other news sources. By utilizing a signature system, each environment can quickly capture sensitive information like Acquisition/Sale of organization, or honeypot data to find the insider leaks.

AI Generated Summary^{may contain errors}

Here is a summarized version of the content:

The speaker is demonstrating an audio transcription system that can detect sensitive information such as credit card numbers and social security numbers. The system uses audio files in GSM format, which are converted to PCM format before processing. The output logs contain information about the conversation, including the time, originator, recipient, duration, and direction of the call.

The speaker uploads two sample audio files to demonstrate the system’s capabilities. The first file is successfully transcribed, detecting a credit card number and social security number. However, the second file fails to detect any curse words due to limitations in the language model used.

The speaker notes that the system is not perfect and may fail to detect certain types of speech patterns or dialects. Future work includes training the system to handle different dialects and languages. The speaker also mentions that dictionaries for major languages such as Spanish, German, and French are available.

Finally, the speaker invites questions from the audience and thanks them for their attention.