This book constitutes revised selected papers from the workshops Nemesis, UrbReas, SoGood, IWAISe, and Green Data Mining, held at the 18th European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2018, in Dublin, Ireland, in September 2018. The 20 papers presented in this volume were carefully reviewed and selected from a total of 32 submissions.

The workshops included are: Nemesis 2018: First Workshop on Recent Advances in Adversarial Machine Learning

UrbReas 2018: First International Workshop on Urban Reasoning from Complex Challenges in Cities SoGood 2018: Third Workshop on Data Science for Social Good

IWAISe 2018: Second International Workshop on Artificial Intelligence in Security Green Data Mining 2018: First International Workshop on Energy Efficient Data Mining and Knowledge Discovery

Inhalt

Label Sanitization against Label Flipping Poisoning Attacks.- Limitations of the Lipschitz constant as a Defense Against Adversarial Examples.- Understanding Adversarial Space through the Lens of Attribution.- Detecting Potential Local Adversarial Examples for Human-Interpretable Defense.- Smart Cities with Deep Edges.- Computational Model for Urban Growth Using Socioeconomic Latent Parameters.- Object Geolocation from Crowdsourced Street Level Imagery.- Extending Support Vector Regression to Constraint Optimization: Application to the Reduction of Potentially Avoidable Hospitalizations.- SALER: a Data Science Solution to Detect and Prevent Corruption in Public Administration.- MaaSim: A Liveability Simulation for Improving the Quality of Life in Cities.- Designing Data-Driven Solutions to Societal Problems: Challenges and Approaches.- Host based Intrusion Detection System with Combined CNN/RNN Model.- Cyber Attacks against the PC Learning Algorithm.- Neural Networks in an Adversarial Setting and Ill-Conditioned Weight Space.- Pseudo-Random Number Generation using Generative Adversarial Networks.- Context Delegation for Context-Based Access Control.- An Information Retrieval System For CBRNe Incidents.- A Virtual Testbed for Critical Incident Investigation with Autonomous Remote Aerial Vehicle Surveying, Artificial Intelligence, and Decision Support.- Event relevancy pruning in support of energy-efficient sequential pattern mining.- How to Measure Energy Consumption in Machine Learning Algorithms.