diff --git a/sca/ascad/.gitignore b/sca/ascad/.gitignore
index a2a8af1..7493065 100644
--- a/sca/ascad/.gitignore
+++ b/sca/ascad/.gitignore
@@ -1 +1,2 @@
 /ASCAD_databases
+__pycache__
diff --git a/sca/ascad/attack.py b/sca/ascad/attack.py
index cf7b84f..33e26e4 100644
--- a/sca/ascad/attack.py
+++ b/sca/ascad/attack.py
@@ -6,8 +6,10 @@ logger = logging.getLogger(__name__)
 import h5py
 import matplotlib.pyplot as plt
 import numpy
+import scipy.fft
 import scipy.signal
 import tqdm
+# import opt_einsum
 
 import numpy_popcount
 
@@ -79,6 +81,7 @@ def align(db, ntraces):
 # P - (n,m) array of n predictions for each of the m candidates
 # O - (n,t) array of n traces with t samples each
 # returns an (m,t) correlation matrix of m traces t samples each
+# TODO : is opt_einsum faster?
 class Correlator:
     def __init__(self, P):
         self.P = P - numpy.mean(P, axis=0)
@@ -118,6 +121,80 @@ def attack_firstorder(db, traces, ntraces):
     plt.show()
 
 
+def attack_firstorder_fft(db, traces, ntraces):
+    # lol
+    ntraces = 2000
+    db = h5py.File("./ASCAD_databases/ASCAD_desync100.h5", "r")["Attack_traces"]
+    traces = db["traces"][0:ntraces, :].astype("double")
+
+    logger.info("making first order model")
+    model = numpy.repeat(numpy.arange(256, dtype='uint8'), ntraces).reshape((256, ntraces))
+    for i in tqdm.trange(ntraces):
+        (pt, ct, key, mask, desync) = db["metadata"][i]
+        pt_v = pt[2]
+        mask_v = mask[15]
+        model[:, i] = AES_SBOX[model[:, i] ^ pt_v] ^ mask_v
+    model = numpy_popcount.popcount(model).astype("double").transpose()
+
+    logger.info("making fft traces")
+    fft_traces = numpy.zeros(traces.shape, traces.dtype)
+    for i in range(traces.shape[0]):
+        fft_traces[i, :] = numpy.abs(scipy.fft.fft(traces[i, :]))
+
+    traces = fft_traces[:, 1:350]
+    avg = numpy.mean(traces, axis=0)
+    peaks = avg.argsort()[-50:][::-1]
+    traces = numpy.hstack([traces[:, i:i+1] for i in peaks])
+
+    correlator = Correlator(model)
+    coefs = correlator.corr_submatrix(traces)
+
+    # plot absmax
+    coefs = numpy.abs(coefs)
+    max_by_key = numpy.max(coefs, axis=1)
+    plt.plot(max_by_key)
+    plt.show()
+
+
+# def attack_secondorder_fft(db, traces, ntraces):
+#     # needs work
+#     # lol
+#     ntraces = 10000
+#     db = h5py.File("./ASCAD_databases/ASCAD.h5", "r")["Attack_traces"]
+#     traces = db["traces"][0:ntraces, :].astype("double")
+#
+#     logger.info("making second order model")
+#     model = numpy.repeat(numpy.arange(256, dtype='uint8'), ntraces).reshape((256, ntraces))
+#     for i in tqdm.trange(ntraces):
+#         (pt, ct, key, mask, desync) = db["metadata"][i]
+#         pt_v = pt[2]
+#         mask_v = mask[15]
+#         model[:, i] = AES_SBOX[model[:, i] ^ pt_v] ^ mask_v
+#     model = numpy_popcount.popcount(model).astype("double").transpose()
+#
+#     logger.info("making fft traces")
+#     fft_traces = numpy.zeros((traces.shape[0], traces.shape[1]), traces.dtype)
+#     for i in range(traces.shape[0]):
+#         fft_i = numpy.abs(scipy.fft.fft(traces[i, :]))
+#         conv_i = numpy.abs(numpy.conj(fft_i) * fft_i)
+#         fft_traces[i, :] = conv_i
+#
+#     traces = fft_traces
+#     # traces = fft_traces[:, 1:350]
+#     # avg = numpy.mean(traces, axis=0)
+#     # peaks = avg.argsort()[-50:][::-1]
+#     # traces = numpy.hstack([traces[:, i:i+1] for i in peaks])
+#
+#     correlator = Correlator(model)
+#     coefs = correlator.corr_submatrix(traces)
+#
+#     # plot absmax
+#     coefs = numpy.abs(coefs)
+#     max_by_key = numpy.max(coefs, axis=1)
+#     plt.plot(max_by_key)
+#     plt.show()
+
+
 def attack_secondorder(db, traces, ntraces):
     logger.info("making second order model")
     model = numpy.repeat(numpy.arange(256, dtype='uint8'), ntraces).reshape((256, ntraces))
@@ -157,6 +234,11 @@ def attack_secondorder(db, traces, ntraces):
 
 def main(db):
     ntraces = 2000
+
+    # traces = None
+    # attack_firstorder_fft(db, traces, ntraces)
+    # return
+
     traces = align(db, ntraces)
 
     # for i in range(10):