uni.liPersonenverzeichnis

Prof. Dr. Pavel Laskov

Lehrstuhlinhaber
Hilti Lehrstuhl für Daten- und Anwendungssicherheit
Tätigkeit
Pavel Laskov ist Professor am Institut für Wirtschaftsinformatik und Inhaber des Hilti-Lehrstuhls für Daten- und Anwendungssicherheit. Seine Forschung befasst sich mit der Entwicklung von Techniken zur Erkennung und Aufklärung von Sicherheitsvorfällen. Dabei werden als wichtiges technisches Werkzeug die auf Cybersicherheit abgestimmte KI-Techniken eingesetzt. Neben den klassischen Zielen der Angriffserkennng eignen sich KI-Techniken insbesondere für fortgeschrittene Aufgaben wie Analyse von Logdateien, Korrelation der Alarme, forensische Untersuchungen sowie Threat-Intelligence. Auf Grund der steigenden Bedeutung der KI, insbesondere in sicherheitskritischen Systemen wie z.B. 5G-Netzwerke, steht die Erforschung der Angriffe auf KI-Systeme sowie der geeigneten Gegenmassnahmen auch auf der Forschungsagenda des Lehrstuhls.
Ausbildung
1996 — 2001

University of Delaware (USA), PhD in Computer Science

1994 — 1996

University of Delaware (USA), MSc in Computer Science

1988 — 1996

Moscow Institute of Radio, Electronics and Automation, Diplom in Computer and Systems Engineering

Werdegang
seit 2018

Universität Liechtenstein, Professor. Inhaber des Hilti Lehrstuhls für Daten- und Anwendungssicherheit

2014 — 2018

Huawei European Research Center (München), Principal Engineer, Leiter des "Big Data Threat Analysis" Teams

2009 — 2014

Universität Tübingen, Heisenberg Stipendiat

2001 — 2009

Fraunhofer Institut für Rechnerarchitektur und Softwaretechnik (Berlin), Projekt- und Forschungsgruppenleiter

1996 — 2001

University of Delaware (USA), Doktorand

1996

AT&T Research (USA), Praktikant

Portrait
Sicherheit von Deep-Learning und Robustheit gegen natürliche Adversarial-Examples
Vorstudie zur Dissertation, seit September 2020

Im Gegensatz zur IT-Sicherheit hat bisher die Betriebssicherheit (Safety) von Lernalgorithmen in der wissenschaftlichen Gemeinschaft relativ wenig Beachtung gefunden. Für vertrauenswürdige KI-Systeme ... mehr

Meeting Industrial Demand for Skills in Information Security Education
ERASMUS, Oktober 2019 bis September 2021

tbc mehr

Detection of Malicious Cryptomining in Network Metadata
FFF-Förderprojekt, Dezember 2018 bis Januar 2019 (abgeschlossen)

Kryptowährungen und denen zu Grunde liegenden Blockchain-Technologien sind eine der faszinierendsten Entwicklungen in der Informationstechnologie im letzten Jahrzehnt. Der Markt für Kryptowährungen ... mehr

  • Srndic, N., & Laskov, P. (2016). Hidost: a static machine-learning-based detector of malicious files. EURASIP Journal on Information Security, 2016(22).

    details
  • Grozea, C., & Laskov, P. (2012). Anomaly detection at "supersonic" speed. Information Technology, 54(2), 82-89.

    details
  • Kloft, M., & Laskov, P. (2012). Security analysis of online centroid anomaly detection. Journal of Machine Learning Research, 13(1), 3133-3176.

    details
  • Henneges, C., Laskov, P., Darmawan, E., Backhaus, J., Kammerer, B., & Zell, A. (2010). A factorization method for the classification of infrared spectra. BMC Bioinformatics, 11(1), 561-572.

    details
  • Wahl, S., Rieck, K., Domschitz, P., Laskov, P., & Müller, K.-R. (2009). Securing MMoIP systems against novel threats. Bell Labs Technical Journal, 14(1), 243-257.

    details
  • Rieck, K., & Laskov, P. (2008). Linear-time computation of similarity measures for sequential data. Journal of Machine Learning Research, 9, 23-48.

    details
  • Krüger, T., Gehl, C., Rieck, K., & Laskov, P. (2008). An architecture for inline anomaly detection. European Conference on Computer Network Defense, 11-18.

    details
  • Rieck, K., & Laskov, P. (2007). Language models for detection of unknown attacks in network traffic. Journal in Computer Virology, 2(4), 243-256.

    details
  • Laskov, P., Gehl, C., Krüger, S., & Müller, K.-R. (2006). Incremental support vector learning: Analysis, implementation and applications. Journal of Machine Learning Research, 7, 1909-1936.

    details
  • Laskov, P., Schäfer, C., Kotenko, I., & Müller, K.-R. (2004). Intrusion detection in unlabeled data with quarter-sphere Support Vector Machines. Praxis der Informationsverarbeitung und Kommunikation, 27(4), 228-236.

    details
  • Ziehe, A., Laskov, P., Notel, G., & Müller, K.-R. (2004). A fast algorithm for joint diagonalization with non-orthogonal transformations and its application to blind source separation. Journal of Machine Learning Research, 5, 777-800.

    details
  • Kambhamettu, C., Goldgof, D., He, M., & Laskov, P. (2003). 3D nonrigid motion analysis under small deformations. Image and Vision Computing, 21(3), 229-245.

    details
  • Laskov, P., & Kambhamettu, C. (2003). Curvature-based algorithms for non-rigid motion and correspondence estimation. IEEE Transations on Pattern Analysis and Machine Intelligence, 25(10), 1349-1354.

    details
  • Laskov, P. (2002). Feasible direction decomposition algorithms for training support vector machines. Machine Learning, 46(1-3), 315-349.

    details
  • Büschkes, R., & Laskov, P. (2006). Detection of Intrusions and Malware & Vul- nerability Assessment : Springer.

    details
  • Laskov, P., Rieck, K., & Müller, K.-R. (2008). Machine learning for intrusion detection. In Mining Massive Data Sets for Security (pp. 366-373): IOS Press.

    details
  • Mika, S., Schäfer, C., Laskov, P., Tax, D., & Müller, K.-R. (2004). Handbook of Computational Statistics. In ch. Support Vector Machines (pp. 841-876): Springer.

    details
  • Srndic, N., & Laskov, P. (2014). Practical evasion of a learning-based classifier: A case study. Paper presented at the IEEE Symposium on Security and Privacy.

    details
  • Biggio, B., Corona, I., Maiorca, D., Nelson, B., Srndic, N., Laskov, P., Giacinto, G., & Roli, F. (2013). Evasion attacks against machine learning at test time. Paper presented at the European Conference on Machine Learning.

    details
  • Srndic, N., & Laskov, P. (2013). Detection of malicious PDF files based on hierarchical document structure. Paper presented at the 20th Network and Distributed Systems Symposium.

    details
  • Biggio, B., Nelson, B., & Laskov, P. (2012). Poisoning attacks against support vector machines. Paper presented at the International Conference on Machine Learning.

    details
  • Biggio, B., Nelson, B., & Laskov, P. (2011). Support vector machines under adversarial label noise. Paper presented at the Asian Conference on Machine Learning.

    details
  • Laskov, P., & Srndic, N. (2011). Static detection of malicious JavaScript-bearing PDF documents. Paper presented at the Annual Computer Security Applications Conference.

    details
  • Nelson, B., Biggio, B., & Laskov, P. (2011). Microbagging estimators: An ensemble approach to distance-weighted classifiers. Paper presented at the Asian Conference on Machine Learning.

    details
  • Nelson, B., Biggio, B., & Laskov, P. (2011). Understanding the risk factors of learning in adversarial environments. Paper presented at the ACM Workshop on Artificial Intelligence and Security.

    details
  • Grozea, C., Bankovic, Z., & Laskov, P. (2010). FPGA vs. multi-core CPUs vs. GPUs: Hands-on experience with sorting. Paper presented at the Facing the Multi-Core Challenge: Conference for Young Scientists, Heidelberger Akademie der Wissenschaften.

    details
  • Kloft, M., Brefeld, U., Sonnenburg, S., Laskov, P., Müller, K.-R., & Zien, A. (2010). Efficient and accurate Lp-Norm MKL.. Paper presented at the Advances in Neural Information Processing Systems 21.

    details
  • Klkoft, M., & Laskov, P. (2010). Online anomaly detection under adversarial impact. Paper presented at the Proceedings of the International Conference on Artificial Intelligence and Statistics.

    details
  • Krüger, T., Gehl, C., Rieck, K., & Laskov, P. (2010). TokDoc: A self-healing web application firewall. Paper presented at the ACM Symposium on Applied Computing.

    details
  • Rieck, K., Schwenk, G., Limmer, T., Holz, T., & Laskov, P. (2010). Botzilla: Detecting the "phoning home" of malicious software. Paper presented at the ACM Symposium on Applied Computing.

    details
  • Düssel, P., Gehl, C., Laskov, P., Störmann, C., Busser, J.-U., & Kästner, J. (2009). Cyber-critical infrastructure protection using real-time payload-based anomaly detection. Paper presented at the Workshop on Critical Information Infrastructures Security.

    details
  • Haage, D., Holz, R., Nidermayer, H., & Laskov, P. (2009). CLIO - A cross-layer information service for overlay network optimization. Paper presented at the Kommunikation in Verteilten Systemen, KiVS 2009, 16. Fachtagung.

    details
  • Laskov, P., & Kloft, M. (2009). A framework for quantitative security analysis of machine learning. Paper presented at the ACM Workshop on Artificial Intelligence and Security.

    details
  • Rieck, K., & Laskov, P. (2009). Visualization and explanation of payload-based anomaly detection. Paper presented at the European Conference on Computer Network Defense.

    details
  • Düssel, P., Gehl, C., Laskov, P., & Rieck, K. (2008). Incorporation of application layer protocol syntax into anomaly detection. Paper presented at the International Conference on Information Systems Security.

    details
  • Franc, V., Laskov, P., & Müller, K.-R. (2008). Stopping conditions for exact compu- tation of leave-one-out error in support vector machines.. , Interna tional Conference on Machine Learning.

    details
  • Kloft, M., Brefeld, U., Düssel, P., Gehl, C., & Laskov, P. (2008). Automatic fea ture selection for anomaly detection. Paper presented at the ACMWorkshop on Artificial Intelligence and Security.

    details
  • Rieck, K., Holz, T., Willems, K., Düssel, P., & Laskov, P. (2008). Learning and classification of malware behavior. Paper presented at the Detection of Intrusions and Malware & Vulnera- bility Assessment.

    details
  • Rieck, K., Wahl, S., Laskov, P., Domschitz, P., & Müller, K.-R. (2008). Self- learning system for detection of anomalous SIP messages. Paper presented at the Principles, Systems and Applications of IP Telecommunications.

    details
  • Rieck, K., Laskov, P., & Sonnenburg, S. (2007). Computation of similarity measures for sequential data using generalized suffix trees. Paper presented at the Advances in Neural Information Processing Systems.

    details
  • Rieck, K., & Laskov, P. (2006). Detecting unknown network attacks using language models. Paper presented at the Detection of Intrusions and Malware & Vulnerability Assessment.

    details
  • Rieck, K., Laskov, P., & Müller, K.-R. (2006). Efficient algorithms for similarity measures over sequential data: A look beyond kernels. Paper presented at the DAGM Symposium on Pattern Recognition.

    details
  • Laskov, P., Düssel, P., Schäfer, C., & Riech, K. (2005). Learning intrusion detection: supervised or unsupervised?. Paper presented at the International Conference on Image Analysis and Processing.

    details
  • Laskov, P., Rieck, K., Schäfer, C., & Müller, K.-R. (2005). Visualization of anomaly detection using prediction sensitivity. Paper presented at the In Sicherheit - Schutz und Zuverlässigkeit.

    details
  • Laskov, P., Schäfer, C., & Kotenko, I. (2004). Intrusion detection in unlabeled data with quarter-sphere Support Vector Machines. Paper presented at the Detection of Intrusions and Malware & Vulnerability Assessment.

    details
  • von Wrede, C., & Laskov, P. (2004). Using classification to determine the number of finger strokes on a multi-touch tactile device. Paper presented at the European Symposium on Artificial Neural Networks.

    details
  • Tasx, D., & Laskov, P. (2003). OnlineSVM learning: from classification to data description and back. Paper presented at the IEEE Workshop on Neural Networks for Signal Processing.

    details
  • Ziehe, A., Laskov, P., Müller, K.-R., & Nolte, G. (2003). A linear least-squares algorithm for joint diagonalization. Paper presented at the International Symposium on Independent Component Analysis and Blind Source Separation.

    details
  • Laskov, P., & Kambhamettu, C. (2002). Curvature-based algorithms for non-rigid motion and correspondence estimation. Paper presented at the Asian Conference on Computer Vision.

    details
  • Laskov, P., & Kambhamettu, C. (2001). Comparison of 3D algorithms for non-rigid motion and correspondence estimation. Paper presented at the British Machine Vision Conference.

    details
  • Laskov, P., & Kambhamettu, C. (2001). Kernel method for linear operator variational problems: non-linear unit normal algorithm for non-rigid motion estimation of 3D sur- faces. Paper presented at the Artificial Neural Networks - ICANN2001, workshop on kernel and subspace methods for computer vision.

    details
  • Laskov, P. (2000). An improved decomposition algorithm for regression support vector machines. , Advances in Neural Information Processing Systems 12.

    details
  • Laskov, P., & Kambhamettu, C. (2000). Tracking non-rigid objects using functional distance metric. Paper presented at the Indian Conference on Computer Vision, Graphics and Image Processing.

    details
  • Erenshteyn, R., Laskov, P., Saxe, D., & Foulds, R. (1999). Distributed output encoding for multi-class pattern recognition. Paper presented at the International Conference on Image Analysis and Processing.

    details
  • Erenshteyn, R., Laskov, P., & Foulds, R. (1997). Human gesture recognition using neural networks and multi-class encoding. Paper presented at the Artificial Neural Networks in Engineering Conference.

    details
  • Erenshteyn, R., & Laskov, P. (1996). multi-stage approach to fingerspelling and gesture recognition. Paper presented at the Workshop on the Integration of Gesture in Language and Speech.

    details
  • Erenshteyn, R., Laskov, P., Foulds, R., Messing, L., & Stern, G. (1996). Recognition approach to gesture language understanding. Paper presented at the International Conference on Pattern Recognition.

    details
  • Laskov, P. (2001). Extensions of differential-geometric algorithms for estimation of 3D non-rigid motion and correspondence. Unpublished Doctoral Thesis, University of Delaware.

    details