1 code implementation • 6 Oct 2023 • Rony Abecidan, Vincent Itier, Jérémie Boulanger, Patrick Bas, Tomáš Pevný
By exploring a grid of processing pipelines fostering CSM, we discovered a geometrical metric based on the chordal distance between subspaces spanned by DCTr features, that exhibits high correlation with operational regret while being not affected by the cover-stego balance.
2 code implementations • 26 May 2023 • Jaromír Janisch, Tomáš Pevný, Viliam Lisý
Current frameworks for training offensive penetration testing agents with deep reinforcement learning struggle to produce agents that perform well in real-world scenarios, due to the reality gap in simulation-based frameworks and the lack of scalability in emulation-based frameworks.
1 code implementation • 8 May 2023 • Vít Škvára, Tomáš Pevný, Václav Šmídl
The area under receiver operating characteristics (AUC) is the standard measure for comparison of anomaly detectors.
1 code implementation • 7 Nov 2022 • Rony Abecidan, Vincent Itier, Jérémie Boulanger, Patrick Bas, Tomáš Pevný
Within an operational framework, covers used by a steganographer are likely to come from different sensors and different processing pipelines than the ones used by researchers for training their steganalysis models.
no code implementations • 4 Aug 2022 • Tomáš Pevný, Viliam Lisý, Branislav Bošanský, Petr Somol, Michal Pěchouček
Learning from raw data input, thus limiting the need for feature engineering, is a component of many successful applications of machine learning methods in various domains.
no code implementations • NeurIPS 2021 • Milan Papež, Tomáš Pevný, Václav Šmídl
The performance of our method is illustrated in a variety of synthetic and real-data contexts, considering deep models, such as mixtures of normalizing flows and sum-product (transform) networks.
1 code implementation • 11 Dec 2020 • Vít Škvára, Jan Franců, Matěj Zorek, Tomáš Pevný, Václav Šmídl
The objective of this comparison is twofold: to compare anomaly detection methods of various paradigms with focus on deep generative models, and identification of sources of variability that can yield different results.
1 code implementation • 25 Sep 2020 • Jaromír Janisch, Tomáš Pevný, Viliam Lisý
We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and object-centric actions.
4 code implementations • NeurIPS 2020 • Niklas Heim, Tomáš Pevný, Václav Šmídl
Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training.
no code implementations • 25 Feb 2020 • Lukáš Adam, Václav Mácha, Václav Šmídl, Tomáš Pevný
Many binary classification problems minimize misclassification above (or below) a threshold.
no code implementations • 2 Dec 2019 • Niklas Heim, Václav Šmídl, Tomáš Pevný
We aim to identify the generating, ordinary differential equation (ODE) from a set of trajectories of a partially observed system.
1 code implementation • 20 Nov 2019 • Jaromír Janisch, Tomáš Pevný, Viliam Lisý
In this work, we extend an existing deep reinforcement learning-based algorithm with hierarchical deep sets and hierarchical softmax, so that it can directly process this data.
2 code implementations • 5 Sep 2019 • Jaromír Janisch, Tomáš Pevný, Viliam Lisý
This work focuses on a specific classification problem, where the information about a sample is not readily available, but has to be acquired for a cost, and there is a per-sample budget.
1 code implementation • 28 May 2019 • Václav Šmídl, Jan Bím, Tomáš Pevný
Reconstruction error is a prevalent score used to identify anomalous samples when data are modeled by generative models, such as (variational) auto-encoders or generative adversarial networks.
no code implementations • ICLR 2019 • Tomáš Pevný, Vojtěch Kovařík
This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures.
1 code implementation • 13 Jul 2018 • Vít Škvára, Tomáš Pevný, Václav Šmídl
Many deep models have been recently proposed for anomaly detection.
1 code implementation • 20 Nov 2017 • Jaromír Janisch, Tomáš Pevný, Viliam Lisý
We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost.
2 code implementations • 5 May 2017 • Jan Stiborek, Tomáš Pevný, Martin Rehák
This work addresses classification of unknown binaries executed in sandbox by modeling their interaction with system resources (files, mutexes, registry keys and communication with servers over the network) and error messages provided by the operating system, using vocabulary-based method from the multiple instance learning paradigm.
Cryptography and Security