🍩 Database of Original & Non-Theoretical Uses of Topology

1. Topological Detection of Trojaned Neural Networks (2021)

   Songzhu Zheng, Yikai Zhang, Hubert Wagner, Mayank Goswami, Chao Chen

   Abstract

   Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited. Guided by basic neuroscientific principles, we discover subtle -- yet critical -- structural deviation characterizing Trojaned models. In our analysis we use topological tools. They allow us to model high-order dependencies in the networks, robustly compare different networks, and localize structural abnormalities. One interesting observation is that Trojaned models develop short-cuts from shallow to deep layers. Inspired by these observations, we devise a strategy for robust detection of Trojaned models. Compared to standard baselines it displays better performance on multiple benchmarks.

   Community Resources

   • Video

   • URL
   • Export citation

   • convolutional neural networks
   • convolutional neural networks:cybersecurity
   • cybersecurity
   • cybersecurity:AI security
   • cybersecurity:Trojan attack
   • cybersecurity:backdoor attacks
   • machine learning
   • Point cloud
   • Point cloud:High Dimension
   • probability vectors
   • Innovate
   • Persistent homology
   • Persistent homology:Rips
   • Persistent homology:representative cycles

2. Cybersecurity Challenges in Downstream Steel Production Processes (2022)

   Joaquín Ordieres-Meré, Andreas Wolff, Antonia Pacios-Álvarez, Antonio Bello-García

   Abstract

   The goal of this paper is to explore proposals coming from different EU-RFCS research funded projects, in such a way that cybersecurity inside the steel industry can be increased from the Operational Technology area, with the current level of adopted Information Technology solutions. The dissemination project Control In Steel has reviewed different projects with different strategies, including ideas to be developed inside the Auto Surveillance project. An advanced control process strategy is considered and cloud based solutions are the main analysed alternatives. The different steps in the model lifecycle are considered where different cloud configurations provide different solutions. Advanced techniques such as UMAP projection are proposed to be used as detectors for anomalous behaviour in the continuous development / continuous implementation strategy, suitable for integration in processing workflows

   • URL
   • DOI
   • Export citation

   • cybersecurity
   • industry
   • industry:steel
   • Time series
   • UMAP