1 code implementation • 11 Jan 2024 • Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck, Kirill Bykov
Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown.
1 code implementation • 23 Oct 2023 • Erwin Quiring, Andreas Müller, Konrad Rieck
Unfortunately, this preprocessing step is vulnerable to so-called image-scaling attacks where an attacker makes unnoticeable changes to an image so that it becomes a new image after scaling.
1 code implementation • 1 Oct 2023 • Lukas Seidel, Sedick David Baker Effendi, Xavier Pinho, Konrad Rieck, Brink van der Merwe, Fabian Yamaguchi
Comparing our approach against recent neural type inference systems, our model outperforms the current state-of-the-art by 7. 85% on the ManyTypes4TypeScript benchmark, achieving 71. 27% accuracy overall.
Ranked #1 on Type prediction on ManyTypes4TypeScript
no code implementations • 17 Apr 2023 • Alexander Warnecke, Julian Speith, Jan-Niklas Möller, Konrad Rieck, Christof Paar
In this paper, we challenge this assumption and introduce a backdoor attack that completely resides within a common hardware accelerator for machine learning.
1 code implementation • 25 Mar 2023 • Thorsten Eisenhofer, Erwin Quiring, Jonas Möller, Doreen Riepel, Thorsten Holz, Konrad Rieck
In this paper, we show that this automation can be manipulated using adversarial learning.
1 code implementation • 26 Aug 2022 • Micha Horlboge, Erwin Quiring, Roland Meyer, Konrad Rieck
We prove that the task of generating a $k$-anonymous program -- a program that cannot be attributed to one of $k$ authors -- is not computable in the general case.
1 code implementation • 25 May 2022 • Vera Wesselkamp, Konrad Rieck, Daniel Arp, Erwin Quiring
In particular, we show that an adversary can remove indicative artifacts, the GAN fingerprint, directly from the frequency spectrum of a generated image.
1 code implementation • 26 Aug 2021 • Alexander Warnecke, Lukas Pirch, Christian Wressnegger, Konrad Rieck
In this paper, we propose the first method for unlearning features and labels.
no code implementations • 19 Oct 2020 • Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro, Konrad Rieck
With the growing processing power of computing systems and the increasing availability of massive datasets, machine learning algorithms have led to major breakthroughs in many different areas.
1 code implementation • 19 Oct 2020 • Erwin Quiring, Lukas Pirch, Michael Reimsbach, Daniel Arp, Konrad Rieck
Consequently, adversaries will also target the learning system and use evasion attacks to bypass the detection of malware.
no code implementations • 19 Mar 2020 • Erwin Quiring, Konrad Rieck
By combining poisoning and image-scaling attacks, we can conceal the trigger of backdoors as well as hide the overlays of clean-label poisoning.
2 code implementations • 5 Jun 2019 • Alexander Warnecke, Daniel Arp, Christian Wressnegger, Konrad Rieck
Deep learning is increasingly used as a building block of security systems.
1 code implementation • 29 May 2019 • Erwin Quiring, Alwin Maier, Konrad Rieck
In this paper, we present a novel attack against authorship attribution of source code.
no code implementations • 25 Nov 2018 • Battista Biggio, Konrad Rieck, Davide Ariu, Christian Wressnegger, Igino Corona, Giorgio Giacinto, Fabio Roli
Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for antivirus systems.
no code implementations • 1 Jun 2017 • Bhargava Shastry, Federico Maggi, Fabian Yamaguchi, Konrad Rieck, Jean-Pierre Seifert
In this paper, we use static template matching to find recurrences of fuzzer-discovered vulnerabilities.
Cryptography and Security Programming Languages Software Engineering
no code implementations • 28 Apr 2017 • Ambra Demontis, Marco Melis, Battista Biggio, Davide Maiorca, Daniel Arp, Konrad Rieck, Igino Corona, Giorgio Giacinto, Fabio Roli
To cope with the increasing variability and sophistication of modern attacks, machine learning has been widely adopted as a statistically-sound tool for malware detection.
Cryptography and Security
no code implementations • 16 Mar 2017 • Erwin Quiring, Daniel Arp, Konrad Rieck
This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods.
no code implementations • 19 Oct 2016 • Christian Wressnegger, Kevin Freeman, Fabian Yamaguchi, Konrad Rieck
Although anti-virus software has significantly evolved over the last decade, classic signature matching based on byte patterns is still a prevalent concept for identifying security threats.
Cryptography and Security
3 code implementations • 28 Dec 2015 • Aylin Caliskan, Fabian Yamaguchi, Edwin Dauber, Richard Harang, Konrad Rieck, Rachel Greenstadt, Arvind Narayanan
Many distinguishing features present in source code, e. g. variable names, are removed in the compilation process, and compiler optimization may alter the structure of a program, further obscuring features that are known to be useful in determining authorship.
Cryptography and Security
no code implementations • 23 Jan 2014 • Nico Goernitz, Marius Micha Kloft, Konrad Rieck, Ulf Brefeld
Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions.