A fearless group of 13 SBA fighters dared to challenge each other at laser tag on April 16.
As an ambassador for Young Science, Katharina Krombholz visits elementary schools all over Austria to give insights into how the internet works. Informing children about related dangers and ways to protect themselves is a special concern of the ambassador program.
Dimitris Simos chairs the Seventh International Workshop on Combinatorial Testing (IWCT 2018) on April 13, 2018.
Kristoffer Kleine presents the paper “CAmetrics: A Tool for Advanced Combinatorial Analysis and Measurement of Test Sets” (joint work with Manuel Leithner and Dimitris E. Simos).
IWCT 2018 takes place in Västerås, Sweden and is collocated with ICST 2018, the 11th IEEE International Conference on Software Testing, Verification and Validation during April 9-13, 2018.
Our Decentralized Systems Group and Edgar Weippl organized together with Foteini Baldimtsi (George Mason University – Fairfax, US), Stefan Katzenbeisser (TU Darmstadt, DE) and Volkmar Lotz (SAP Labs France – Mougins, FR) the Dagstuhl Seminar on Blockchains, Smart Contracts and Future Applications, which takes place this week at Schloss Dagstuhl in Germany.
26 participants are discussing interesting scientific topics linked to blockchain, smart contracts and future applications. Further information can be found on the website of Dagstuhl.
Dimitris Simos (SBA Research) and Rick Kuhn (NIST) are presenting a crash course on combinatorial security testing at the Symposium and Bootcamp for Hot Topics in the Science of Security (HotSoS ’18).
The event takes place at Raleigh, NC, USA and is sponsored by the NSA in cooperation with ACM SIGSAC.
Futurezone.at reports on an initiative that KSÖ starts jointly with SBA Research “Gemeinsam mit SBA Research startet das KSÖ deshalb Anfang April die Initiative ‘Sicherheitsforum Digitale Wirtschaft Österreich’.”
Deadline for manuscript submissions: 31 October 2018
Machine learning is clearly a research area that will continue creating real-world impact, as computing power becomes increasingly more readily available. Security and privacy considerations, however, are vital, in particular since machine learning algorithms are often perceived as magical black boxes, in which the inner workings are not easily made transparent. Important topics that warrant new research are, among others:
The right to be forgotten. How much of the ‘original’ personal data is embedded in trained neural networks? Can we delete this data without retraining? How can we measure the anonymity/pseudonymity of training data embedded in a trained network?
How easy is it to attack training sets and trained networks? If ML is used for real-world applications such as autonomous driving, successful attacks may have huge impact.
We look forward to receiving research papers that address, not only the aforementioned examples, but also any excellent research that investigates privacy and security aspects in ML in depth.
Edgar Weippl, Francesco Buccafurri, Guest Editors
- Threat models
- Attacks against machine learning
- Malware detection
- Black-box attacks against machine learning
- Adversarial training and defensive distillation
- Privacy-preserving machine learning
- Application of machine learning to security and privacy
The 11th Plenary of the Research Data Alliance was held 21-23 March 2018 in Berlin under the theme “From Data to Knowledge”. The meeting has gathered scientists, experts and practitioners engaged in the advancement of data-driven science and economy from around the world.
Tomasz Miksa chaired a session of the DMP Common Standards working group. He also presented current achievements of the group and announced new open consultation on standards for common data model for machine-actionable data management plans.
The detailed agenda and collaborative notes can be found here.
To follow the activities and learn more about the DMP Commons Standards WG please visit its official web page.
— Tomasz Miksa (@miksa_tomasz) March 21, 2018
Ludwig successfully defended his Master Thesis “Combinatorial and Algorithmic Constructions of Covering Arrays” advised by Dimitris E. Simos,at the Faculty of Mathematics and Geoinformation of TU Vienna. Ludwig gave an excellent presentation and graduated with distinction.