"This site requires JavaScript to work correctly"
minimize Header

Prof. Dr. Michael Heigl

Artificial Intelligence for Cybersecurity

Centre for Applied Research

TC Vilshofen

Professor

ITC2+ 1.04

0991/3615-537

consulting time

please contact me by email for an appointment

Sortierung:
Vortrag

  • Michael Heigl

Cybersicherheit – Mehr als nur ein Kostenfaktor?!

In: Netzwerk.Wirtschaft Vilshofen

Pro Vilshofen Stadtmarketing e.V. Vilshofen

  • 13.03.2023 (2023)
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Amar Almaini
  • Jakob Folz
  • D. Wölfl
  • A. Al Dubai
  • Martin Schramm
  • Michael Heigl

A New Scalable Distributed Homomorphic Encryption Scheme for High Computational Complexity Models

  • (2023)
Due to the increasing privacy demand in data processing, Fully Homomorphic Encryption (FHE) has recently received growing attention for its ability to perform calculations over encrypted data. Since the data can be processed in encrypted form and the output remains encrypted, only an authorized user or a user who holds the key can decrypt the data and understand its meaning. Hence, it is possible to securely outsource data processing to untrustworthy but powerful public computing resources on the edge. However, due to the high computational complexity, FHE-based data processing experiences scalability related concerns. It is currently unclear whether FHE can be used to solve large-scale problems. In this paper, we propose a novel general distributed FHE-based data processing approach as a concrete step towards solving the scalability challenge. The main idea behind our approach is to use slightly more communication overhead for a shorter computing circuit in FHE, hence, reducing the overall complexity. We verify our new model’s efficiency and effectiveness by comparing the distributed approach with the central approach over various FHE schemes (CKKS, BGV, and BFV). This is performed using one of the more popular libraries of FHE “Microsoft SEAL”, by performing specific mathematical operations and observing the time consumed. The empirical results demonstrate that the proposed approach results in a significant reduction in time, up to 54% compared to the traditional central approach.
  • Institut ProtectIT
  • DIGITAL
Vortrag

  • Jakob Folz
  • Robert Aufschläger
  • Michael Heigl

PRIVATE OPEN DATA?! - EAsyAnon TRUSTSERVICE. Posterpräsentation

In: Nationale Konferenz IT-Sicherheitsforschung 2023 - Die digital vernetzte Gesellschaft stärken

Bundesministerium für Bildung und Forschung Berlin

  • 13.-15.03.2023 (2023)
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Institut ProtectIT
  • DIGITAL
Zeitschriftenartikel

  • Michael Heigl
  • Kumar Anand
  • Andreas Urmann
  • D. Fiala
  • Martin Schramm
  • Robert Hable

On the Improvement of the Isolation Forest Algorithm for Outlier Detection with Streaming Data

In: Electronics vol. 10 pg. 1534.

  • (2021)

DOI: 10.3390/electronics10131534

In recent years, detecting anomalies in real-world computer networks has become a more and more challenging task due to the steady increase of high-volume, high-speed and high-dimensional streaming data, for which ground truth information is not available. Efficient detection schemes applied on networked embedded devices need to be fast and memory-constrained, and must be capable of dealing with concept drifts when they occur. Different approaches for unsupervised online outlier detection have been designed to deal with these circumstances in order to reliably detect malicious activity. In this paper, we introduce a novel framework called PCB-iForest, which generalized, is able to incorporate any ensemble-based online OD method to function on streaming data. Carefully engineered requirements are compared to the most popular state-of-the-art online methods with an in-depth focus on variants based on the widely accepted isolation forest algorithm, thereby highlighting the lack of a flexible and efficient solution which is satisfied by PCB-iForest. Therefore, we integrate two variants into PCB-iForest—an isolation forest improvement called extended isolation forest and a classic isolation forest variant equipped with the functionality to score features according to their contributions to a sample’s anomalousness. Extensive experiments were performed on 23 different multi-disciplinary and security-related real-world datasets in order to comprehensively evaluate the performance of our implementation compared with off-the-shelf methods. The discussion of results, including AUC, F1 score and averaged execution time metric, shows that PCB-iForest clearly outperformed the state-of-the-art competitors in 61% of cases and even achieved more promising results in terms of the tradeoff between classification and computational costs.
  • Institut ProtectIT
  • Elektrotechnik und Medientechnik
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Zeitschriftenartikel

  • Michael Heigl
  • Enrico Weigelt
  • Andreas Urmann
  • D. Fiala
  • Martin Schramm

Exploiting the Outcome of Outlier Detection for Novel Attack Pattern Recognition on Streaming Data

In: Electronics vol. 10 pg. 2160.

  • (2021)

DOI: 10.3390/electronics10172160

Future-oriented networking infrastructures are characterized by highly dynamic Streaming Data (SD) whose volume, speed and number of dimensions increased significantly over the past couple of years, energized by trends such as Software-Defined Networking or Artificial Intelligence. As an essential core component of network security, Intrusion Detection Systems (IDS) help to uncover malicious activity. In particular, consecutively applied alert correlation methods can aid in mining attack patterns based on the alerts generated by IDS. However, most of the existing methods lack the functionality to deal with SD data affected by the phenomenon called concept drift and are mainly designed to operate on the output from signature-based IDS. Although unsupervised Outlier Detection (OD) methods have the ability to detect yet unknown attacks, most of the alert correlation methods cannot handle the outcome of such anomaly-based IDS. In this paper, we introduce a novel framework called Streaming Outlier Analysis and Attack Pattern Recognition, denoted as SOAAPR, which is able to process the output of various online unsupervised OD methods in a streaming fashion to extract information about novel attack patterns. Three different privacy-preserving, fingerprint-like signatures are computed from the clustered set of correlated alerts by SOAAPR, which characterizes and represents the potential attack scenarios with respect to their communication relations, their manifestation in the data’s features and their temporal behavior. Beyond the recognition of known attacks, comparing derived signatures, they can be leveraged to find similarities between yet unknown and novel attack patterns. The evaluation, which is split into two parts, takes advantage of attack scenarios from the widely-used and popular CICIDS2017 and CSE-CIC-IDS2018 datasets. Firstly, the streaming alert correlation capability is evaluated on CICIDS2017 and compared to a state-of-the-art offline algorithm, called Graph-based Alert Correlation (GAC), which has the potential to deal with the outcome of anomaly-based IDS. Secondly, the three types of signatures are computed from attack scenarios in the datasets and compared to each other. The discussion of results, on the one hand, shows that SOAAPR can compete with GAC in terms of alert correlation capability leveraging four different metrics and outperforms it significantly in terms of processing time by an average factor of 70 in 11 attack scenarios. On the other hand, in most cases, all three types of signatures seem to reliably characterize attack scenarios such that similar ones are grouped together, with up to 99.05% similarity between the FTP and SSH Patator attack.
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Institut ProtectIT
  • DIGITAL
Zeitschriftenartikel

  • Michael Heigl
  • Enrico Weigelt
  • D. Fiala
  • Martin Schramm

Unsupervised Feature Selection for Outlier Detection on Streaming Data to Enhance Network Security

In: Applied Sciences vol. 11 pg. 12073.

  • (2021)

DOI: 10.3390/app112412073

Over the past couple of years, machine learning methods—especially the outlier detection ones—have anchored in the cybersecurity field to detect network-based anomalies rooted in novel attack patterns. However, the ubiquity of massive continuously generated data streams poses an enormous challenge to efficient detection schemes and demands fast, memory-constrained online algorithms that are capable to deal with concept drifts. Feature selection plays an important role when it comes to improve outlier detection in terms of identifying noisy data that contain irrelevant or redundant features. State-of-the-art work either focuses on unsupervised feature selection for data streams or (offline) outlier detection. Substantial requirements to combine both fields are derived and compared with existing approaches. The comprehensive review reveals a research gap in unsupervised feature selection for the improvement of outlier detection methods in data streams. Thus, a novel algorithm for Unsupervised Feature Selection for Streaming Outlier Detection, denoted as UFSSOD, will be proposed, which is able to perform unsupervised feature selection for the purpose of outlier detection on streaming data. Furthermore, it is able to determine the amount of top-performing features by clustering their score values. A generic concept that shows two application scenarios of UFSSOD in conjunction with off-the-shell online outlier detection algorithms has been derived. Extensive experiments have shown that a promising feature selection mechanism for streaming data is not applicable in the field of outlier detection. Moreover, UFSSOD, as an online capable algorithm, yields comparable results to a state-of-the-art offline method trimmed for outlier detection. V
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Elektrotechnik und Medientechnik
  • DIGITAL
Zeitschriftenartikel

  • Michael Heigl
  • Laurin Dörr
  • Nicolas Tiefnig
  • D. Fiala
  • Martin Schramm

A Resource-Preserving Self-Regulating Uncoupled MAC Algorithm to be Applied in Incident Detection

In: Computers & Security vol. 85 pg. 270-285.

  • (2019)

DOI: 10.1016/j.cose.2019.05.010

The connectivity of embedded systems is increasing accompanied with thriving technology such as Internet of Things/Everything (IoT/E), Connected Cars, Smart Cities, Industry 4.0, 5G or Software-Defined Everything. Apart from the benefits of these trends, the continuous networking offers hackers a broad spectrum of attack vectors. The identification of attacks or unknown behavior through Intrusion Detection Systems (IDS) has established itself as a conducive and mandatory mechanism apart from the protection by cryptographic schemes in a holistic security eco-system. In systems where resources are valuable goods and stand in contrast to the ever increasing amount of network traffic, sampling has become a useful utility in order to detect malicious activities on a manageable amount of data. In this work an algorithm – Uncoupled MAC – is presented which secures network communication through a cryptographic scheme by uncoupled Message Authentication Codes (MAC) but as a side effect also provides IDS functionality producing alarms based on the violation of Uncoupled MAC values. Through a novel self-regulation extension, the algorithm adapts it’s sampling parameters based on the detection of malicious actions. The evaluation in a virtualized environment clearly shows that the detection rate increases over runtime for different attack scenarios. Those even cover scenarios in which intelligent attackers try to exploit the downsides of sampling.
  • Institut ProtectIT
  • Elektrotechnik und Medientechnik
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Michael Heigl
  • Laurin Dörr
  • Martin Schramm
  • D. Fiala

On the Energy Consumption of Quantum-resistant Cryptographic Software Implementations Suitable for Wireless Sensor Networks

pg. 72-83.

  • (2019)

DOI: 10.5220/0007835600720083

For an effective protection of the communication in Wireless Sensor Networks (WSN) facing e.g. threats by quantum computers in the near future, it is necessary to examine the applicability of quantum-resistant mechanisms in this field. It is the aim of this article to survey possible candidate schemes utilizable on sensor nodes and to compare the energy consumption of a selection of freely-available software implementations using a WSN-ready Texas Instruments CC1350 LaunchPad ARM® Cortex®-M3 microcontroller board.
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Elektrotechnik und Medientechnik
  • DIGITAL
  • NACHHALTIG
Beitrag in Sammelwerk/Tagungsband

  • Michael Heigl
  • Martin Schramm
  • D. Fiala

A Lightweight Quantum-Safe Security Concept for Wireless Sensor Network Communication

pg. 906-911.

  • (2019)

DOI: 10.1109/PERCOMW.2019.8730749

The ubiquitous internetworking of devices in all areas of life is boosted by various trends for instance the Internet of Things. Promising technologies that can be used for such future environments come from Wireless Sensor Networks. It ensures connectivity between distributed, tiny and simple sensor nodes as well as sensor nodes and base stations in order to monitor physical or environmental conditions such as vibrations, temperature or motion. Security plays an increasingly important role in the coming decades in which attacking strategies are becoming more and more sophisticated. Contemporary cryptographic mechanisms face a great threat from quantum computers in the near future and together with Intrusion Detection Systems are hardly applicable on sensors due to strict resource constraints. Thus, in this work a future-proof lightweight and resource-aware security concept for sensor networks with a processing stage permeated filtering mechanism is proposed. A special focus in the concepts evaluation lies on the novel Magic Number filter to mitigate a special kind of Denial-of-Service attack performed on CC1350 LaunchPad ARM Cortex-M3 microcontroller boards.
  • Elektrotechnik und Medientechnik
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Institut ProtectIT
  • DIGITAL
  • MOBIL
Beitrag in Sammelwerk/Tagungsband

  • Laurin Dörr
  • Michael Heigl
  • D. Fiala
  • Martin Schramm

Comparison of Energy-Efficient Key Management Protocols for Wireless Sensor Networks

pg. 21-26.

  • (2019)

DOI: 10.1145/3343147.3343156

A Wireless Sensor Network (WSN) contains small sensor nodes which monitor physical or environmental conditions. WSN is an important technology for digitalization of industrial periphery and is often used in environments which are not hardened against security impacts. These networks are easy to attack due to the open communication medium and low computing resources of the applied devices. Establishing security mechanisms is difficult while taking into account low energy consumption. Low cost sensors with limited resources make the implementation of cryptographic algorithms even more challenging. For WSNs cryptographic functions are needed without high impact on energy consumption and latency. Therefore, security in WSNs is a challenging field of research. This paper compares lightweight energy-efficient key exchange protocols which are suitable for WSN. The protocols were also implemented in WSN-capable Texas Instrument boards and the energy consumption was measured during the key exchange. This paper shows that schemes have to be chosen depending on the specific network requirements and that the usage of asymmetric cryptography does not always result in a high energy consumption.
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • DIGITAL
  • NACHHALTIG
Vortrag

  • Michael Heigl

DecADe - Decentralized Anomaly Detection . Posterpräsentation

In: 5. Tag der Forschung

Technische Hochschule Deggendorf Deggendorf

  • 08.03.2018 (2018)
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Michael Heigl
  • Laurin Dörr
  • Amar Almaini
  • D. Fiala
  • Martin Schramm

Incident Reaction Based on Intrusion Detections’ Alert Analysis

pg. 1-6.

  • (2018)

DOI: 10.23919/AE.2018.8501419

The protection of internetworked systems by cryptographic techniques have crystallized as a fundamental aspect in establishing secure systems. Complementary, detection mechanisms for instance based on Intrusion Detection Systems has established itself as a fundamental part in holistic security eco-systems in the previous years. However, the interpretation of and reaction on detected incidents is still a challenging task. In this paper an incident handling environment with relevant components and exemplary functionality is proposed that involves the processes from the detection of incidents over their analysis to the execution of appropriate reactions. An evaluation of a selection of implemented interacting components using technology such as OpenFlow or Snort generally proofs the concept.
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Zeitschriftenartikel

  • Martin Schramm
  • R. Dojen
  • Michael Heigl

A Vendor-Neutral Unified Core for Cryptographic Operations in GF(p) and GF( 2m ) Based on Montgomery Arithmetic (Article ID 4983404)

In: Security and Communication Networks pg. 1-18.

  • (2018)

DOI: 10.1155/2018/4983404

In the emerging IoT ecosystem in which the internetworking will reach a totally new dimension the crucial role of efficient security solutions for embedded devices will be without controversy. Typically IoT-enabled devices are equipped with integrated circuits, such as ASICs or FPGAs to achieve highly specific tasks. Such devices must have cryptographic layers implemented and must be able to access cryptographic functions for encrypting/decrypting and signing/verifying data using various algorithms and generate true random numbers, random primes, and cryptographic keys. In the context of a limited amount of resources that typical IoT devices will exhibit, due to energy efficiency requirements, efficient hardware structures in terms of time, area, and power consumption must be deployed. In this paper, we describe a scalable word-based multivendor-capable cryptographic core, being able to perform arithmetic operations in prime and binary extension finite fields based on Montgomery Arithmetic. The functional range comprises the calculation of modular additions and subtractions, the determination of the Montgomery Parameters, and the execution of Montgomery Multiplications and Montgomery Exponentiations. A prototype implementation of the adaptable arithmetic core is detailed. Furthermore, the decomposition of cryptographic algorithms to be used together with the proposed core is stated and a performance analysis is given.
  • Institut ProtectIT
  • Elektrotechnik und Medientechnik
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Zeitschriftenartikel

  • Nari Arunraj
  • Robert Hable
  • Michael Fernandes
  • Karl Leidl
  • Michael Heigl

Comparison of Supervised, Semi-supervised and Unsupervised Learning Methods in Network Intrusion Detection Systems (NIDS) Application

In: Anwendungen und Konzepte in der Wirtschaftsinformatik (AKWI) pg. 10-19.

  • (2017)
With the emergence of the fourth industrial revolution (Industrie 4.0) of cyber physical systems, intrusion detection systems are highly necessary to detect industrial network attacks. Recently, the increase in application of specialized machine learning techniques is gaining critical attention in the intrusion detection community. A wide variety of learning techniques proposed for different network intrusion detection system (NIDS) problems can be roughly classified into three broad categories: supervised, semi-supervised and unsupervised. In this paper, a comparative study of selected learning methods from each of these three kinds is carried out. In order to assess these learning methods, they are subjected to investigate network traffic datasets from an Airplane Cabin Demonstrator. In addition to this, the imbalanced classes (normal and anomaly classes) that are present in the captured network traffic data is one of the most crucial issues to be taken into consideration. From this investigation, it has been identified that supervised learning methods (logistic and lasso logistic regression methods) perform better than other methodswhen historical data on former attacks are available. The results of this study have also showed that the performance of semi-supervised learning method (One class support vector machine) is comparatively better than unsupervised learning method (Isolation Forest) when historical data on former attacks are not available.
  • TC Grafenau
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • TC Teisnach Sensorik
  • Institut ProtectIT
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Martin Schramm
  • R. Dojen
  • Michael Heigl

Experimental assessment of FIRO- and GARO-based noise sources for digital TRNG designs on FPGAs

pg. 1-6.

  • (2017)

DOI: 10.23919/AE.2017.8053618

The quality of TRNG designs mainly depends on the grade of the noise source from which the entropy will be harvested to extract randomness. Especially for purely digital noise sources suitable for FPGA implementations the use of Ring Oscillators is suggested in many scientific publications. Standard Ring Oscillator based noise sources however have earned some criticism regarding the amount of entropy generated. On this account different enhancements have been proposed, with Fibonacci Ring Oscillators (FIROs) and Galois Ring Oscillators (GAROs) being prominent examples, which under some circumstances are able to sustain a chaotic oscillation suitable for entropy extraction. This paper deals with the assessment of fully constrained FIRO and GARO noise source designs for a specific target FPGA. Due to the restrictive placement of ring elements the assessment yielded new criteria for choosing proper FIRO/GARO feedback configurations and an enhanced sampling method for entropy extraction has been derived.
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Laurin Dörr
  • D. Fiala
  • Michael Heigl
  • Martin Schramm

Assessment simulation model for uncoupled message authentication

  • (2017)

DOI: 10.23919/AE.2017.8053580

Today's trend of an increasing number of networked embedded devices pervades many areas. Ranging from home automation, industrial or automotive applications with a large number of different protocols, low resources and often high demands on real-time make it difficult to secure the communication of such systems. A concept of an uncoupled MAC which is able to ensure the authenticity and integrity of communication flows between two network parties can be used. This is in particular of advance for outdated legacy components still participating in the network. In this paper a assessment simulation model of the mechanism behind this technology is described. It outlines the probability of detecting an attack depending on the message authentication overhead. The model considers all control variables and performs measurements based on random data traffic. The results of the statistical analysis state that a high attack detection rate can be obtained even with a small communication overhead.
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL
Vortrag

  • Karl Leidl
  • Martin Aman
  • Michael Heigl
  • Andreas Grzemba

Intrusion Detection Sensoren für industrielle Netzwerke

In: CYBICS - Cyber Security for Industrial Control Systems (Workshop & Konferenz für IT-Sicherheit in der Industrie)

Würzburg

  • 22.-23.06.2016 (2016)
  • TC Teisnach Sensorik
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
Beitrag in Sammelwerk/Tagungsband

  • Michael Heigl
  • Martin Schramm
  • Laurin Dörr
  • Andreas Grzemba

Embedded Plug-In Devices to Secure Industrial Network Communications

  • (2016)
  • Elektrotechnik und Medientechnik
  • Institut ProtectIT
  • 30 S: TC Vilshofen S_EN: TC Vilshofen
  • DIGITAL