Skip to main content
Version: 4.0.0-rc1

Replay Attack Detection

Phonexia has developed Replay Attack Detection technology as part of its Deepfake Detection suite. This technology is designed to identify the unauthorized use of stolen or recorded audio data that is replayed without the consent of the original speaker. Such attacks often aim to deceive speaker verification systems by impersonating legitimate users.

Replay attacks typically involve the playback of previously recorded audio samples to gain fraudulent access or manipulate voice-based authentication systems.

Phonexia's detection approach is based on the insight that audio recordings carry not only the speaker’s voice but also acoustic artifacts from the recording environment — such as room reverberation, microphone quality, background noise, and transmission characteristics. These subtle cues can help differentiate between live and replayed audio.

Possible use cases​

  • Voice biometric system protection: Preventing unauthorized access to secure systems that use voice as an authentication method (e.g., banking apps, smart devices).
  • Fraud prevention in call centers: Detecting replayed audio clips used by fraudsters attempting to impersonate customers during service interactions.

Scoring​

Score values range from negative infinity to positive infinity. The score is a Log-Likelihood Ratio (LLR), which measures the strength of the evidence supporting either hypothesis:

  • Values closer to negative infinity suggest the evidence is more likely under Hypothesis 0 ("genuine/live speech").
  • Values closer to positive infinity suggest the evidence is more likely under Hypothesis 1 ("replay attack").

The output score is calibrated such that 0 corresponds to the Equal Error Rate (EER) point on our evaluation datasets. The EER is the point at which the false acceptance rate and false rejection rate are equal, providing a balanced trade-off between the two.

Depending on your specific use case and the characteristics of your data, you may need to adjust the decision threshold to achieve the desired balance between false positives and false negatives.