24 August 2017

RICS will host a one day tutorial and seminar on deep learning methods that will take place at Linköping University, IDA , B building, entry 29, 1 floor up, Room Von Neumann.

Patrick Glauner (from University of Luxembourg) will have a presentation divided  in three parts.

  1. An introduction to deep learning (11.00-12.00)

This part is a joint seminar with the SaS division at IDA and can be skipped by people who already have some background in the area, or just be attended by people who want a basic orientation.

2. Advanced tutorial on deep learning (13.15-15.00)

This part is a continuation from the morning session but uses a deeper analysis of the methods.

3. Application of machine learning to electricity theft (15.15-17.00)

This is a talk decoupled from the previous ones and describes an application of machine learning (not deep learning).

Here is the abstracts for the different parts:

(1) and  (2): Title: Deep Learning on Big Data Sets in the Cloud with Apache Spark and Google TensorFlow

Patrick GLAUNER and Radu STATE, Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg

Abstract: Machine learning is the branch of artificial intelligence giving computers the ability to learn patterns from data without being explicitly programmed. Deep Learning is a set of cutting-edge machine learning algorithms that are inspired by how the human brain works. It allows to selflearn feature hierarchies from the data rather than modeling hand-crafted features. It has proven to significantly improve performance in challenging data analytics problems. In this tutorial, we will first provide an introduction to the theoretical foundations of neural networks and Deep Learning. Second, we will demonstrate how to use Deep Learning for character recognition in a cloud using a distributed environment for Big Data analytics. This combines Apache Spark and TensorFlow, Google’s in-house Deep Learning platform made for Big Data machine learning applications.

(3)  Title: Detecting Electricity Theft using Machine Learning

Patrick GLAUNER and Radu STATE, Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg

Abstract: Detection of non-technical losses (NTL) which include electricity theft, faulty meters or billing errors has attracted attention from researchers in electrical engineering and computer science. NTLs cause significant harm to the economy, as in some countries they may range up to 40% of the total electricity distributed. The predominant research direction is employing artificial intelligence (AI) to solve this problem. Promising approaches have been reported falling into two categories: expert systems incorporating hand-crafted expert knowledge or machine learning which learns fraudulent consumption patterns from examples without being explicitly programmed. In order to detect NTL, inspections of customers are carried out based on predictions. However, carrying out inspections is costly, as it requires physical presence of technicians. In this talk, we will present our research progress in predicting NTL more accurately. We will also outline future challenges of our research and how we intend to address them.

Speaker: Patrick GLAUNER is a PhD student at the University of Luxembourg working on the detection of electricity theft through machine learning. He graduated as valedictorian from Karlsruhe University of Applied Sciences with a BSc in computer science and obtained his MSc in machine learning from Imperial College London. He was a CERN Fellow, worked at SAP and is an alumnus of the German National Academic Foundation (Studienstiftung des deutschen Volkes). He is also adjunct lecturer of artificial intelligence at Karlsruhe University of Applied Sciences. His current interests include anomaly detection, big data, computer vision, deep learning and time series.

7-9 June 2017

RICS researchers will participate and present in the national SWITS seminar for researchers on information security, which will be held in collaboration with the COINS network in Norway this year.

30th May – 1 June 2017

The Spring term thesis presentations will include topics related to RICS research.

At Linköping, B Building, Donald Knuth, the following presentations will take place 30th May:

11-12 Evaluating the performance of a fault-tolerant system that implements replicaton and load balancing

13-14 Functional and security testing of a mobile system

If interested to attend, email Simin.Nadjm-Tehrani @ liu.se

At Chalmers EDIT building, Johanneberg the following presentations will be made on 1st June:

0930-10 Welcome and coffee

10–11 Fuzzing the S7 protocol

11-12 A network-based Intrusion Detection System for Indusitral Control Systems

12-13 Lunch

If interested to attend, email Magnus.Almgren  @ Chalmers.se

17-18 May 2017

To further increase the awareness of the need for cyber security, RICS researcher will participate in Elkraft 2017 with a poster. The event brings together industry, researchers and students to discuss and plan the future grid in Sweden.

22 February 2017

RICS holds a joint workshop with the second MSB-financed Project CERCES at MSB premises. The stakeholders in our reference Group and the invitees are welcome! Here is a link to the program.

2 November 2016 at 13:15-14:15

A seminar by Gunnar Björkman (with decades of experience at ABB)  will be held on the topic of SCADA systems for electrical grids – their use and their design.

Location: Room Von Neumann. Linköping University, Campus Valla, B Building, 1 floor up, between entry 29 and 27, B corridor.

Abstract: A short presentation of modern SCADA systems for electrical grids starting with a background why they are needed and how they have developed from isolated stand-alone systems to integrated solutions with office applications. Basic SCADA applications including process communication/RTUs and Human Machine interfaces will be included. Advanced applications for grid security and optimization will be discussed. The presentation will focus on usage and user benefits of SCADA systems but some basic design issues like process communication principles, real-time databases, performance and availability will be described. The intention is to have an open discussion during the presentation.

27 October 2016

Simin Nadjm-Tehrani will present work from the RICS research centre at 4SICS Stockholm.

9-10 June 2016

The annual SWITS Conference held by the Swedish network of information security researchers financed by MSB was hosted by Linköping University this year. The program included several presentations by PhD students from Swedish universities and invited talks by Ivan Buetler (CompasSecurity) and Peter Ryan (University of Luxembourg).

12-13 April 2016

Annual EBITS meeting for energy sector companies discussing security concerns was held in Linköping with  around 50 participants. Preliminary program and some slides from the talks can be accessed.

7th April 2016 at 13:15-14:15

RICS organises a seminar by Yulia Cherdantseva from Cardiff University on the topic of risk assessment.

Location: Room Von Neumann. Linköping University, Campus Valla, B Building, 1 floor up, between entry 29 and 27, B corridor.

Abstract: Recently, in the framework of SCADA Cyber Security Lifecycle (SCADA-CSL) programme funded by the Airbus Group Endeavr Wales we have conducted a review of cyber security risk assessment methods for Supervisory Control and Data Acquisition (SCADA) systems . The review is presented here. This paper is currently the most downloaded article at Computers & Security.

In this talk I will cover the results of our review as well as the review methodology and research challenges identified. For the review, we selected and in-detail examined twenty-four risk assessment methods developed for or applied in the context of a SCADA system. We analysed the methods in terms of aim; application domain; the stages of risk management addressed; key risk management concepts covered; impact measurement; sources of probabilistic data; evaluation and tool support. Based on the analysis, we suggested an intuitive scheme for the categorisation of cyber security risk assessment methods for SCADA systems. Most importantly, we outlined five research challenges facing risk assessment in SCADA systems and pointed out the approaches that might be taken.

16th December 2015 at 15-17

The RICS research centre organizes two seminars back-to-back by Ketil Stølen, a world authority on risk assessment for IT systems.

The first talk targets a broader audience (practitioners, and researchers not specialised in risk analysis) and the second talk targets researchers with interest in IT security risk research. The abstract of the talks are presented here.

Location: Linköping University, Campus Valla, Room Donald Knuth, B Bldg entry 29, one floor up, B corridor.

Talk 1, 15.15-16.00 ————

Cyber-risk management — What are the real challenges?

These days the EU, government bodies, standards and regulations make heavy use of buzzwords prefixed by “cyber”. Unfortunately, the same bodies are very unclear wrt what these terms actually mean as well as their practical implications. This talk represents an attempt to sort out this mess. I will characterize to what extent cybersecurity and cyber-risk represents something new and identify what I see as the real challenges in this context. I will discuss challenges such as measurement, uncertainty, risk aggregation and black-Swans.

The talk is based on a new book on cyber risk management.

Talk 2, 16.15-17.00 ———–

Uncertainty, Subjectivity, Trust and Risk: How It All Fits Together

Trust management involves the identification and analysis of trust relations.

However, adequately managing trust requires all the relevant aspects of trust to be addressed. Moreover, which aspects to address depend on the perspective of the trust management. In this talk we relate the notion of trust to the notions of uncertainty, subjectivity and risk, and we explain how these aspects should be addressed and reasoned about from three different perspectives.