TUM Logo

Huang Xiao

Huang Xiao

Alumni

E-Mail:
now at Fraunhofer AISEC

 

Research Interests

My research interests include adversarial and secure machine learning, anomaly detection, semi-supervised learning, nonparametric learning. I am generally interested at machine learning and its applicaitons. Now I focus on applying machine learning on cyber security problems.

I am currently working at Fraunhofer AISEC Institute. Check my personal web for more: huangxiao.de
Teaching
SS 2012 Seminar : Machine Learning in Adversarial Environment
SS 2013 Seminar : Machine Learning in Adversarial Environment
WS 2014 Practical Course: Anomaly Detection Challenges (firstly established practical course)
SS 2015

Seminar: Adversarial Machine Learning
SS 2016

Selected Advanced Topics on Cyber Security

Applied Machine Learning on Cyber Security: An Overview
Adversarial Learning: AI as a New Security Threat

 

 

 

Supervised Student Works
Sami Ghawi.

Spatio-Temporal Anomaly Detection in Mobile Devices.

Master Thesis, Technische Universität München, Oct. 2013.
Heeren Sharma.

Concept Learner for CorMel Transaction Trees in Amadeus Data Processing Systems.

Master Thesis, Technische Universität München, Mar. 2014.
Aleieldin Salam.

Semantic-based Malware Detection with Hidden Markov Model.

Guided Research, July 2015.
Dieu Linh Tran.

Incremental One-Class Support Vector Machines with Minor Supervised Labels.

Master Thesis, Technische Universität München, Oct. 2015.
Jan Lauinger.

Large Scale Anomaly Detection using Spark.

Bachelor Thesis, Technische Universität München, Aug. 2016 (in progress).

 

 

 

 

Publications

2019   Stack Overflow Considered Helpful! Deep Learning Security Nudges Towards Stronger Cryptography

28th USENIX Security Symposium (USENIX Security 19)

2017   Stack overflow considered harmful? The impact of copy&paste on Android application security

IEEE Symposium on Security and Privacy, SP 2017

2015   Is Feature Selection Secure against Training Data Poisoning?

Proceedings of The 32nd International Conference on Machine Learning (ICML'15)

2014   Support Vector Machines under Adversarial Label Contamination

Journal of Neurocomputing, Special Issue on Advances in Learning with Label Noise

2013   Indicative Support Vector Clustering with its Application on Anomaly Detection

IEEE 12th International Conference on Machine Learning and Applications (ICMLA'13)

  Learning from Multiple Observers with Unknown Expertise

Proceedings of 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining

  OPARS: Objective Photo Aesthetics Ranking System

34th European Conference on Information Retrieval (ECIR'13)

2012   Adversarial Label Flips Attack on Support Vector Machines

20th European Conference on Artificial Intelligence (ECAI)

2010   Grammatical Inference Algorithms in MATLAB

ICGI 2010: Proceedings of the 10th International Colloquium on Grammatical Inference