```python import numpy as np import matplotlib.pyplot as plt from scipy.io import wavfile from scipy.signal import butter, lfilter # Load the audio file sample_rate, audio_data = wavfile.read('mastermind.wav') # Function to apply a lowpass filter def butter_lowpass_filter(data, cutoff, fs, order=5): nyquist = 0.5 * fs normal_cutoff = cutoff / nyquist b, a = butter(order, normal_cutoff, btype='low', analog=False) y = lfilter(b, a, data) return y # Apply a lowpass filter cutoff_frequency = 3000 filtered_audio_data = butter_lowpass_filter(audio_data, cutoff_frequency, sample_rate) # Function to perform sliding window FFT def sliding_window_fft(audio, window_size, step_size, sample_rate): fft_values = [] times = [] num_windows = (len(audio) - window_size) // step_size for i in range(num_windows): start = i * step_size end = start + window_size windowed_audio = audio[start:end] * np.hanning(window_size) fft_value = np.fft.fft(windowed_audio) fft_values.append(np.abs(fft_value[:window_size//2])) times.append((start + end) // 2 / sample_rate) return np.array(fft_values).T, np.array(times) # Perform sliding window FFT window_size = 1024 step_size = 256 fft_values, times = sliding_window_fft(filtered_audio_data, window_size, step_size, sample_rate) frequencies = np.fft.fftfreq(window_size, 1/sample_rate)[:window_size//2] # DTMF keypad frequencies mapping low_frequencies = [697, 770, 852, 941] high_frequencies = [1209, 1336, 1477, 1633] dtmf_mapping = { (697, 1209): '1', (697, 1336): '2', (697, 1477): '3', (697, 1633): 'A', (770, 1209): '4', (770, 1336): '5', (770, 1477): '6', (770, 1633): 'B', (852, 1209): '7', (852, 1336): '8', (852, 1477): '9', (852, 1633): 'C', (941, 1209): '*', (941, 1336): '0', (941, 1477): '#', (941, 1633): 'D' } # Find the nearest frequency in the given list def find_nearest_frequency(frequency, frequency_list): return min(frequency_list, key=lambda x: abs(x - frequency)) # Function to format timestamp def format_timestamp(time_in_seconds): seconds = int(time_in_seconds) milliseconds = int((time_in_seconds % 1) * 1000) return f"{seconds}.{milliseconds:03d}" ``` ```python import pandas as pd # Function to detect DTMF tones with top-2 FFT frequencies and detected characters def detect_dtmf_tones_with_characters(fft_values, frequencies, low_frequencies, high_frequencies, dtmf_mapping): detected_tones = [] for i, time_slice in enumerate(fft_values.T): # Find the indices of the two most intensive frequencies top_two_indices = np.argsort(time_slice)[-2:][::-1] top_two_frequencies = frequencies[top_two_indices] top_two_intensities = time_slice[top_two_indices] fft_freq1 = min(top_two_frequencies) fft_freq2 = max(top_two_frequencies) # Identify low and high frequencies based on the top two frequencies low_freq = find_nearest_frequency(fft_freq1, low_frequencies) high_freq = find_nearest_frequency(fft_freq2, high_frequencies) # Map to DTMF character detected_character = dtmf_mapping.get((low_freq, high_freq), None) # Get the corresponding time in seconds time_in_seconds = times[i] # Append to detected tones detected_tones.append((time_in_seconds, low_freq, high_freq, [fft_freq1, fft_freq2], top_two_intensities, detected_character)) return detected_tones # Detect DTMF tones with top-2 FFT frequencies and detected characters detected_tones_with_characters = detect_dtmf_tones_with_characters(fft_values, frequencies, low_frequencies, high_frequencies, dtmf_mapping) # Creating a list of dictionaries for detected tones with characters detected_tones_data_with_characters = [] for result in detected_tones_with_characters: timestamp, low_freq, high_freq, fft_freqs, intensities, character = result detected_tones_data_with_characters.append({ 'timestamp': timestamp, 'low_freq': low_freq, 'high_freq': high_freq, 'fft_freq1': fft_freqs[0], 'fft_freq2': fft_freqs[1], 'intensity1': intensities[0], 'intensity2': intensities[1], 'character': character }) # Converting the list of dictionaries into a pandas DataFrame with characters detected_tones_df_with_characters = pd.DataFrame(detected_tones_data_with_characters) # Displaying the first 10 rows of the DataFrame with characters detected_tones_df_with_characters.head(10) ``` ```python tones = detected_tones_df_with_characters ``` ```python tones = tones[(tones.intensity2 * tones.intensity1) > 1e12] ``` ```python tones.sample(10) ``` ```python tones ``` ```python tones['delta'] = ((tones['fft_freq1'] - tones['low_freq']).abs() * (tones['fft_freq2'] - tones['high_freq']).abs()) ``` /tmp/ipykernel_2009135/824670098.py:1: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: https://pandas.pydata.org/pandas- docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy tones['delta'] = ((tones['fft_freq1'] - tones['low_freq']).abs() * (tones['fft_freq2'] - tones['high_freq']).abs()) ```python ``` ```python tones['delta'].plot() ``` ![png](output_8_1.png) ```python tones = tones[tones['delta'] < 10 ** 4] ``` ```python tones['character_prev'] = tones['character'].shift() ``` /tmp/ipykernel_2009135/3924296832.py:1: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: https://pandas.pydata.org/pandas- docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy tones['character_prev'] = tones['character'].shift() ```python tones_sequence = tones.copy() tones_sequence['sequence_index'] = (~(tones['character'] == tones['character_prev'])).cumsum() # [~(tones['character'] == tones['character_prev'])][['timestamp', 'character']] ``` ```python tones_sequence['count'] = 1 ``` ```python tones_sequence = tones_sequence.groupby('sequence_index').agg({'count': 'sum', 'character': 'first', 'timestamp': 'first'}) ``` ```python tones_sequence['count'] = (tones_sequence['count'] / 28).round().astype(int) ``` ```python tones_sequence['phrase_index'] = ((tones_sequence['timestamp'] - tones_sequence['timestamp'].shift()) / 0.35 > 3).cumsum() ``` ```python tones_sequence = tones_sequence.groupby('phrase_index').agg({'character': list, 'count': list}) ``` ```python tones_sequence.apply(lambda x: ''.join([a * b for a, b in zip(*x)]), axis=1) ``` phrase_index 0 41323036267601217574 1 36710992825315281347 2 60924906937541136999 3 02333 dtype: object ```python value = int(''.join(tones_sequence.apply(lambda x: ''.join([a * b for a, b in zip(*x)]), axis=1))) ``` ```python # Converting to hexadecimal hex_representation = hex(value) hex_representation hex_string = hex_representation[2:] # Removing the '0x' prefix bytes_representation = bytes.fromhex(hex_string) bytes_representation.decode() ``` 'dsc{m0th3r_1s_m0th3r1ng_ts}' ```python ``` Original writeup (https://github.com/dremovd/ctf/blob/main/deconstruct/Mastermind%20(phone%20tones%20recognition).ipynb).