ABOUT NEWS PEOPLE RESEARCH COURSES JOBS
Research
Machine Learning

For Security and Privacy in Machine Learning, we consider the privacy of datasets and the robustness of classifiers against maliciously crafted input. We also consider Machine Learning as a tool for Security and Privacy, for example to detect vulnerabilities or malicious behaviour.

PEOPLE
Martina Lindorfer
Martina Lindorfer
Professor (TU Wien) ↗
Semeen Rehman
Semeen Rehman
Professor (TU Wien) ↗
PUBLICATIONS

EagerNet - Early Predictions of Neural Networks for Computationally Efficient Intrusion Detection. Fares Meghdouri, Maximilian Bachl, Tanja Zseby (eprint)
FlowPrint - Semi-Supervised Mobile-App Fingerprinting on Encrypted Network Traffic. Thijs van Ede, Riccardo Bortolameotti, Andrea Continella, Jingjing Ren, Daniel J. Dubois, Martina Lindorfer, David R. Choffnes, Maarten van Steen, Andreas Peter (NDSS)
Guest Editorial Leveraging Machine Learning in SDN/NFV-Based Networks. David S. L. Wei, Kaiping Xue, Roberto Bruschi, Stefan Schmid (IEEE J. Sel. Areas Commun.)
How Many Bits Does it Take to Quantize Your Neural Network? Mirco Giacobbe, Thomas A. Henzinger, Mathias Lechner (TACAS)
LFQ - Online Learning of Per-flow Queuing Policies using Deep Reinforcement Learning. Maximilian Bachl, Joachim Fabini, Tanja Zseby (eprint)
Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes. Tomás Brázdil, Krishnendu Chatterjee, Petr Novotný, Jiri Vahala (AAAI)
Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes. Tomás Brázdil, Krishnendu Chatterjee, Petr Novotný, Jiri Vahala (eprint)
SSCNets - Robustifying DNNs using Secure Selective Convolutional Filters. Hassan Ali, Faiq Khalid, Hammad Tariq, Muhammad Abdullah Hanif, Rehan Ahmed, Semeen Rehman (IEEE Des. Test)
SparseIDS - Learning Packet Sampling with Reinforcement Learning. Maximilian Bachl, Fares Meghdouri, Joachim Fabini, Tanja Zseby (CNS)
SparseIDS - Learning Packet Sampling with Reinforcement Learning. Maximilian Bachl, Fares Meghdouri, Joachim Fabini, Tanja Zseby (eprint)
When Malware is Packin' Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features. Hojjat Aghakhani, Fabio Gritti, Francesco Mecca, Martina Lindorfer, Stefano Ortolani, Davide Balzarotti, Giovanni Vigna, Christopher Kruegel (NDSS)
An Improved Quick Artificial Bee Colony Algorithm for Portfolio Selection. Dit Suthiwong, Maleerat Sodanil, Gerald Quirchmayr (Int. J. Comput. Intell. Appl.)
Approximate Multi-Accelerator Tiled Architecture for Energy-Efficient Motion Estimation. Bharath Srinivas Prabakaran, Walaa El-Harouni, Semeen Rehman, Muhammad Shafique (Approximate Circuits)
Building Robust Machine Learning Systems - Current Progress, Research Challenges, and Opportunities. Jeff Jun Zhang, Kang Liu, Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Theocharis Theocharides, Alessandro Artussi, Muhammad Shafique, Siddharth Garg (DAC)
DeepMPLS - Fast Analysis of MPLS Configurations Using Deep Learning. Fabien Geyer, Stefan Schmid (Networking)
Designing Worm-inspired Neural Networks for Interpretable Robotic Control. Mathias Lechner, Ramin M. Hasani, Manuel Zimmer, Thomas A. Henzinger, Radu Grosu (ICRA)
Explainability and Adversarial Robustness for RNNs. Alexander Hartl, Maximilian Bachl, Joachim Fabini, Tanja Zseby (eprint)
FAdeML - Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning. Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique (DATE)
Hardware-Software Approximations for Deep Neural Networks. Muhammad Abdullah Hanif, Muhammad Usama Javed, Rehan Hafiz, Semeen Rehman, Muhammad Shafique (Approximate Circuits)
Heterogeneous Approximate Multipliers - Architectures and Design Methodologies. Semeen Rehman, Bharath Srinivas Prabakaran, Walaa El-Harouni, Muhammad Shafique, Jörg Henkel (Approximate Circuits)
Ismael - Using Machine Learning to Predict Acceptance of Virtual Clusters in Data Centers. Johannes Zerwas, Patrick Kalmbach, Stefan Schmid, Andreas Blenk (IEEE Trans. Netw. Serv. Manag.)
Outside the Box - Abstraction-Based Monitoring of Neural Networks. Thomas A. Henzinger, Anna Lukina, Christian Schilling (eprint)
QuSecNets - Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks. Faiq Khalid, Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique (IOLTS)
RED-Attack - Resource Efficient Decision based Attack for Machine Learning. Faiq Khalid, Hassan Ali, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique (eprint)
Rax - Deep Reinforcement Learning for Congestion Control. Maximilian Bachl, Tanja Zseby, Joachim Fabini (ICC)
Strategy Representation by Decision Trees with Linear Classifiers. Pranav Ashok, Tomás Brázdil, Krishnendu Chatterjee, Jan Kretínský, Christoph H. Lampert, Viktor Toman (QEST)
Strategy Representation by Decision Trees with Linear Classifiers. Pranav Ashok, Tomás Brázdil, Krishnendu Chatterjee, Jan Kretínský, Christoph H. Lampert, Viktor Toman (eprint)
Towards Data Anonymization in Data Mining via Meta-heuristic Approaches. Fatemeh Amiri, Gerald Quirchmayr, Peter Kieseberg, Edgar R. Weippl, Alessio Bertone (DPM/CBT@ESORICS)
TrISec - Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks. Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique (IOLTS)
Members
Partners