Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Pevný, Tomáš"'
Deep generative models have recently made a remarkable progress in capturing complex probability distributions over graphs. However, they are intractable and thus unable to answer even the most basic probabilistic inference queries without resorting
Externí odkaz:
http://arxiv.org/abs/2408.09451
Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undi
Externí odkaz:
http://arxiv.org/abs/2408.07394
Detection of malicious behavior in a large network is a challenging problem for machine learning in computer security, since it requires a model with high expressive power and scalable inference. Existing solutions struggle to achieve this feat -- cu
Externí odkaz:
http://arxiv.org/abs/2408.03287
The proliferation of image manipulation for unethical purposes poses significant challenges in social networks. One particularly concerning method is Image Steganography, allowing individuals to hide illegal information in digital images without arou
Externí odkaz:
http://arxiv.org/abs/2405.16961
Explainability of decisions made by AI systems is driven by both recent regulation and user demand. These decisions are often explainable only \emph{post hoc}, after the fact. In counterfactual explanations, one may ask what constitutes the best coun
Externí odkaz:
http://arxiv.org/abs/2401.14086
In imitation learning for planning, parameters of heuristic functions are optimized against a set of solved problem instances. This work revisits the necessary and sufficient conditions of strictly optimally efficient heuristics for forward search al
Externí odkaz:
http://arxiv.org/abs/2310.19463
Publikováno v:
IEEE International Workshop on Information Forensics and Security (WIFS 2023), Dec 2023, Nuremberg, Germany
In operational scenarios, steganographers use sets of covers from various sensors and processing pipelines that differ significantly from those used by researchers to train steganalysis models. This leads to an inevitable performance gap when dealing
Externí odkaz:
http://arxiv.org/abs/2310.04479
In classification and forecasting with tabular data, one often utilizes tree-based models. Those can be competitive with deep neural networks on tabular data and, under some conditions, explainable. The explainability depends on the depth of the tree
Externí odkaz:
http://arxiv.org/abs/2306.06777
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 scalabil
Externí odkaz:
http://arxiv.org/abs/2305.17246
The area under receiver operating characteristics (AUC) is the standard measure for comparison of anomaly detectors. Its advantage is in providing a scalar number that allows a natural ordering and is independent on a threshold, which allows to postp
Externí odkaz:
http://arxiv.org/abs/2305.04754