[Home]

Over-the-wire (OTW) Attack Accuracy (Figure 7)

Environment

• Randomly select 100 commands (with different length: short, medium, and long) from a pool of commonly used voice commands in Amazon Alexa [link] or Google Assistant [link]
• Utilize Google TTS to generate fast speech (adversarial audio) with different playback speed
  (2.0x - 3.0x) [link]
• We setup the following target ASRs
  • Amazon Transcribe [link]
  • Google STT [link]
  • IBM Watson STT [link]
  • Microsoft Azure STT [link]

Experiment Procedure

• Step 1. Generate 1100 (i.e., 11x100) adversarial audio candidates for 100 commands with different lengths (27 short, 26 medium, and 47 long) under varying playback speeds
  (2.0x - 3.0x, increment by 0.1x)
  • Adversarial Audio
• Step 2. Generate 1100 normal audio files with the same playback speed as adversarial audio files
  • Normal Audio
• Step 3. For each ASR, we feed it with corresponding crafted adversarial audio
• Step 4. Compute translation accuracy = number of successful transcriptions / total number of transcription attempts

Result

• Figure 7 in the paper demonstrates translation accuracy for different ASRs.