Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus
Word embedding methods allow to represent words as vectors in a space that is structured using word co-occurrences so that words with close meanings are close in this space. These vectors are then provided as input to automatic systems to solve natural language processing problems. Because interpretability is a necessary condition to trusting such systems, interpretability of embedding spaces, the first link in the chain is an important issue. In this paper, we thus evaluate the interpretability of vectors extracted with two approaches: SPINE a k-sparse auto-encoder, and SINr, a graph-based method. This evaluation is based on a Word Intrusion Task with human annotators. It is operated using a large French corpus, and is thus, as far as we know, the first large-scale experiment regarding word embedding interpretability on this language. Furthermore, contrary to the approaches adopted in the literature where the evaluation is done on a small sample of frequent words, we consider a more realistic use-case where most of the vocabulary is kept for the evaluation. This allows to show how difficult this task is, even though SPINE and SINr show some promising results. In particular, SINr results are obtained with a very low amount of computation compared to SPINE, while being similarly interpretable.
Code (0)
등록된 구현이 없습니다.
Tasks
Intrusion DetectionSimilar Papers 제목 키워드 기반
Are Existing Out-Of-Distribution Techniques Suitable for Network Intrusion Detection?
Machine learning (ML) has become increasingly popular in network intrusion detection. However, ML-based solutions always respond regardless of whether the input data reflects known patterns, a common issue across safety-…
Contrastive LearningIntrusion DetectionNetwork Intrusion DetectionTowards Explainable Meta-Learning for DDoS Detection
The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intel…
Intrusion DetectionMeta-LearningA Hybrid Approach for an Interpretable and Explainable Intrusion Detection System
Cybersecurity has been a concern for quite a while now. In the latest years, cyberattacks have been increasing in size and complexity, fueled by significant advances in technology. Nowadays, there is an unavoidable neces…
Intrusion DetectionFetFIDS: A Feature Embedding Attention based Federated Network Intrusion Detection Algorithm
Intrusion Detection Systems (IDS) have an increasingly important role in preventing exploitation of network vulnerabilities by malicious actors. Recent deep learning based developments have resulted in significant improv…
Network Intrusion DetectionFederated LearningAnomal-E: A Self-Supervised Network Intrusion Detection System based on Graph Neural Networks
This paper investigates Graph Neural Networks (GNNs) application for self-supervised network intrusion and anomaly detection. GNNs are a deep learning approach for graph-based data that incorporate graph structures into …
Anomaly DetectionIntrusion DetectionNetwork Intrusion Detection