Auto encoders are neural networks trained to reconstruct input data. Anomalies are detected via high reconstruction error (MSE).
Key Uses:
Network intrusion detection, fraud detection, and log anomaly identification.
Hacks:
Use Variational Auto encoders (VAEs) for better latent space regularization. Implement denoising autoencoders to improve robustness to noisy inputs. Combine with LSTM layers for sequential network traffic data. Use isolation forests as an ensemble method with autoencoder scores.
References:
An, J., & Cho, S. (2015). Variational Autoencoder based Anomaly Detection using Reconstruction Probability.
