Finding patterns in binary files using deep learning

Question

I am a newbie in deep learning and wanted to know if the problem I have at hand is a suitable fit for deep learning algorithms. I have thousands of fragments each of about 1000 bytes size (i.e. numbers in the range of 0 to 255). There are two classes in the fragments:

Some fragments have a high frequency of two particular byte values appearing next to one another: "0 and 100". This kind of pattern roughly appears once every 100 to 200 bytes. In the other class, the byte values are more randomly distributed. We have the ability to produce as many numbers of instances of each class as needed for training purposes. However, I would like to differentiate with a machine learning algorithm without explicitly identifying the "0 and 100" pattern in the 1st class myself. Can deep learning help us solve this? If so, what kind of layers might be useful?

As a preliminary experiment, we tried to train a deep learning network made up of 2 hidden layers of TensorFlow's "Dense" layers (of size 512 and 256 nodes in each of the hidden layers). However, unfortunately, our accuracy was indicative of simply a random guess (i.e. 50% accuracy). We were wondering why the results were so bad. Do you think a Convolutional Neural Network will better solve this problem?

Answer 1

From the brief description, CNNs would indeed seem much better suited to solve this problem. In particular, the main inductive bias of CNNs is that their is spatial pattern that is translation-invariant, which seems like exactly the case you're describing. If you believe that the patterns you mentioned are simple, then training a small, shallow (1D) CNN should perform well on the task. I hope that helps!