Search papers, labs, and topics across Lattice.
This study investigates the application of JEPA-style predictive learning to network fingerprints derived from the JA4 dataset, aiming to enhance the representation of network traffic for classification tasks. By training the JA4-JEPA model on a diverse set of JA4 subfields, the authors achieved impressive results, including a cosine similarity of 0.9899 and a kNN accuracy of 0.9220 on protocol-family classification tasks across multiple protocols. These findings suggest that predictive learning can effectively generate high-quality embeddings from network fingerprints, even when data is incomplete.
JEPA-style predictive learning can yield remarkably accurate network representations, achieving over 92% accuracy in classifying protocol families from partial data.
I-JEPA and V-JEPA learn by matching latent predictions to target encoder outputs rather than regenerating the original input, and this has worked well for images and video. We explore whether the same objective works for compact network fingerprints. We built JA4-JEPA, a Transformer-based model trained on JA4, JA4H, JA4S, and JA4X subfields drawn from JA4DB and CIC-IDS- 2017. The training data combines roughly 397K samples from both sources, though no single sample contains all four view families. We evaluated the learned representations with a frozen kNN probe on protocol-family classification across TLS, DNS, and SSH. On 39,416 heldout samples the model achieved a cosine similarity of 0.9899 and a kNN accuracy of 0.9220. These results indicate that JEPA-style predictive learning can produce useful embeddings from JA4-derived fingerprints, even with incomplete view overlap across sources. Keywords: JA4, network fingerprinting, JEPA, predictive representation learning, self-supervised learning
