TUM Logo

Anomaly Detection Challenges

Anomaly Detection Challenges  

Praktika 0sws / 10ects
Veranstalter: Bojan Kolosnjaji, Mohammad Reza Norouzian, and George Webster
Zeit und Ort:

Di, 16:30 – 18:00 Uhr, 01.06.011. (Praktikum)

Beginn: 2016-10-18

The lecture is given in english
The slides are available in english

News

 

  • Challenge 2 - maximum number of submissions increased to 10. Have fun overfitting :)
  • Another change in schedule!
  • Challenge 2 started!
  • Small change in schedule: we flipped the content of 13.12. and 20.12. in order to leave more time for Challenge 4.
  • Challenge 1 started!
  • Schedule is published.
  • Selected students are registered in TUMOnline, except for the exchange students, who will be registered in October.
  • Kick-Off meeting: 29.06.2016. at 4pm, Room 01.06.011. If you missed the kick-off meeting, you can look at the slides.

 

Description

In information security domain, anomaly detection gains its own importance from researchers day by day. It is discovered that occasionally emerged frauds or intrusions in modern information systems have incurred significant loss when the suspicious activities were not detected or inefficiently processed. Therefore, numerous efforts have been devoted to devise effective detection methods, and then proceed to automation of anomaly identification in real time. In this practical course, we challenge students with a set of well designated learning tasks, which require the participants to understand the task scenario entirely and to design their own algorithms to identify corresponding anomalies. A competition on discovering the anomalies will be conducted based on the performance of their algorithms.

Requirement

  • Basic knowlege of Machine learning and data mining
  • Good programming skills
  • Basic knowlege in Python
  • Registered Master or Diplom students (or very ambitious Bachelor students) in Informatics or a similar area

Instruction

ResizedImage350500-instruction.png

 

Schedule

Date
Topic
Assignments
18.10.2016.
Anomaly Detection Basics 1
Homework 1, Challenge 1
25.10.2016.
Anomaly Detection Basics 2
Homework 2, Challenge 2 
08.11.2016.
Presentation day 1
None
15.11.2016.
Large-Scale Malware Analysis - extracting the Big Picture (rescheduled)
 
22.11.2016.
Presentation day 2
None
29.11.2016.
Network Anomaly Detection - find a needle in a haystack
Homework 3 (deadline 12.12.), Challenge 3
06.12.2016.
Large-Scale Malware Analysis - extracting the Big Picture
Homework 4 (deadline 19.12.), Challenge 4
13.12.2016.
Presentation day 3
None
20.12.2016.
Spark Tutorial
Homework 5 (deadline 16.01.)
10.01.2016.
Semi-Supervised Learning, Active Learning, Ensemble Learning
Homework 6-7 (deadline 23.01.), Challenge 5
17.01.2016.
Presentation day 4
None
24.01.2016.
Presentation day 5
None

 

 

Contact

Bojan Kolosnjaji

Email: kolosnjaji@sec.in.tum.de

Room: 01.08.061

 

Mohammad Reza Norouzian

Email: norouzian@sec.in.tum.de

Room: 01.08.059

 

George Webster

Email: webstergd@sec.in.tum.de

Room: 01.08.057