NBC-Softmax : Darkweb Author fingerprinting and migration tracking

TL;DR

This paper introduces NBC-Softmax, a contrastive loss-based clustering method that improves author fingerprinting and migration tracking on darkweb forums by outperforming existing softmax-based approaches.

Contribution

The paper proposes NBC-Softmax, a novel contrastive loss technique for softmax that enhances discriminative power and scalability in darkweb author detection tasks.

Findings

Outperforms state-of-the-art methods on darkweb forums

Effective mini-batch sampling for large datasets

Scalable and superior to pair-wise losses

Abstract

Metric learning aims to learn distances from the data, which enhances the performance of similarity-based algorithms. An author style detection task is a metric learning problem, where learning style features with small intra-class variations and larger inter-class differences is of great importance to achieve better performance. Recently, metric learning based on softmax loss has been used successfully for style detection. While softmax loss can produce separable representations, its discriminative power is relatively poor. In this work, we propose NBC-Softmax, a contrastive loss based clustering technique for softmax loss, which is more intuitive and able to achieve superior performance. Our technique meets the criterion for larger number of samples, thus achieving block contrastiveness, which is proven to outperform pair-wise losses. It uses mini-batch sampling effectively and is scalable. Experiments on 4 darkweb social forums, with NBCSAuthor that uses the proposed NBC-Softmax for author and sybil detection, shows that our negative block contrastive approach constantly outperforms state-of-the-art methods using the same network architecture. Our code is publicly available at : https://github.com/gayanku/NBC-Softmax