PhD Scholarship on Adversarial Machine Learning, Belief Propagation Theories and their Applications in Identifying Complex Network Cyber-Security Threats

Wednesday 03 Jul 19

Apply for this job

Apply no later than 30 July 2019
Apply for the job at DTU Compute by completing the following form.

Apply online

The Cyber Security Section at DTU Compute conducts interdisciplinary research in most aspects of computer and information security, ranging from advanced cryptography and access control mechanisms, for ensuring secrecy and authentication in todays’ communications, to the design, analysis and implementation of novel protection mechanisms for enhanced security, privacy, trustworthiness, and reliability in numerous emerging IoT applications. Through methods such as applied cryptography, hardware enhanced security, modelling and security analysis of systems, and verification, we are building security into new technology, providing assurance to the user that they are interacting with a trusted platform. Our research focuses on cryptography; trusted computing; secure communications; privacy and authentication; and security verification – with applications in, e.g., automotive, future Internet and 5G, smart grid, healthcare, e Payment, etc.

Research field of the position
This PhD scholarship is financed by the Innovation Fund Denmark project “Identification of Cyber-Security Threats using Machine Learning (SecDNS)”. The use of machine learning models has become ubiquitous. Their predictions are used to make decisions about a number of critical applications including (amongst others) security in identifying complex cyber-security threats in the context of the Internet (e.g., malicious domains) and other networking environments. These models are widely used in many cyber defence systems for network security operations, malware analysis, etc. But despite the many successes, the very property that makes machine learning desirable: adaptability, is a vulnerability that may be exploited by an attacker that could potentially result in the severe degradation of the integrity, security and performance of cyber defence systems. All machine learning systems are trained using datasets that are assumed to be representative and valid for the subject matter in question.

However, there a number of questions raised:
 

  • Identifying complex cyber-security threats, through developing appropriate classification models, depends heavily on the intelligence database used for training the models. However, how can we make strong arguments and handle the aggregation of such intelligence information with uncertain provenance? Aggregating different indicators of compromise from various information sources demands a means to reason about the correctness, completeness and consistency of provided information.
  • When an event has been identified, the concept of propagating belief about potential malicious entities, in the overall graph of related/involved components, has been partically resolved in the literature. What we need is to specify belief inference and propagation egine based on a detailed feature constraints analysis and trust management of all data sources (internal and external).
  • Malicious actors can impact how the artificial intelligence system functions by poisoning the training data. This threat is exacerbated when the machine learning pipeline that includes data collection, curation, labelling, and training is not controlled completely by the model owner. This project will focus on understanding, evaluating, and improving the effectiveness of machine learning methods in the presence of motivated and sophisticated adversaries.
The objective of this project is to engage artificial intelligence and data science technologies towards developing a unified adversarial classification framework that takes into account uncertainty from data while handling the necessary belief propagation modelling.

Responsibilities and tasks
The primary task of the PhD candidate will be to conduct original research in the area described above with the goal to produce a PhD dissertation by the end of the 3-year program.

The goal is to answer difficult questions concerning adversarial machine learning (that assumes no specific attack, no specific perturbation, and no specific loss function), belief inference and propagation modelling. The research outcomes will expected to be applied in security, intrusion detection and beyond.

The PhD candidate will learn to write articles reporting the original results, of a sufficient high quality to appear in top scientific conferences and journals. He/she will participate in relevant conferences in the relevant field and, as part of the PhD program, he/she may have the opportunity for an external research stay abroad of 3-6 months.

It is a requirement of the program that all PhD students take advanced courses amounting to approximate 30 ECTS points. As part of the salary, there is a requirement of performing additional tasks (about 3 months during the 3 years) in the area of teaching or other departmental work.

Qualifications
Candidates should have a two-year Master’s degree or a similar degree with an academic level equivalent to a two-year MSc degree. A good background in the theory and practice of security and (adversarial) machine learning is essential, and preference will be given to candidates who can demonstrate knowledge on intrusion detection concepts, belief propagation and Bayesian modelling, subjective logic and trust management. Good implementation skills and practical experience are also desirable. Furthermore, good command of the English language is essential.

Approval and Enrolment
The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU PhD Guide.  

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union.

The period of employment is 3 years. Starting date is 1 August 2019 or according to mutual agreement as soon as possible after that.

You can read about career paths at DTU 
here

Further information
Further information concerning the project can be obtained from Christian D. Jensen, mail cdje@dtu.dk, tel. +45 4525 3724 or Athanasios Giannetsos, mail atgi@dtu.dk, tel +45 4525 3009, in the Cyber Security Section at DTU Compute.

Information concerning the application is available at the DTU Compute 
PhD homepage or by contacting PhD coordinator Lene Matthisson +45 4525 3377. 

You can read more about DTU compute at 
compute.dtu.dk/english.  

Application procedure
Please submit your application no later than 30 July 2019 (local time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include: 
  • A letter motivating the application (cover letter)
  • CV
  • Grade transcripts and BSc/MSc diploma
Applications and enclosures received after the deadline will not be considered.

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply.

DTU Compute has a total staff of 400 including 100 faculty members and 130 PhD students. We offer introductory courses in mathematics, statistics, and computer science to all engineering programmes at DTU and specialised courses to the mathematics, computer science, and other programmes. We offer continuing education courses and scientific advice within our research disciplines, and provide a portfolio of innovation activities for students and employees.

DTU is a technical university providing internationally leading research, education, innovation and scientific advice. Our staff of 6,000 advance science and technology to create innovative solutions that meet the demands of society, and our 11,200 students are being educated to address the technological challenges of the future. DTU is an independent academic university collaborating globally with business, industry, government and public agencies.