Search Results for author:
Found 18 papers, 13 papers with code
Leveraging Data Geometry to Mitigate CSM in Steganalysis
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.
NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios
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.
Is AUC the best measure for practical comparison of anomaly detectors?
The area under receiver operating characteristics (AUC) is the standard measure for comparison of anomaly detectors.
Using Set Covering to Generate Databases for Holistic Steganalysis
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.
Explaining Classifiers Trained on Raw Hierarchical Multiple-Instance Data
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.
Fitting large mixture models using stochastic component selection
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.
Comparison of Anomaly Detectors: Context Matters
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.
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition
We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and object-centric actions.
Neural Power Units
Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training.
General Framework for Binary Classification on Top Samples
Many binary classification problems minimize misclassification above (or below) a threshold.
Rodent: Relevance determination in differential equations
We aim to identify the generating, ordinary differential equation (ODE) from a set of trajectories of a partially observed system.
Classification with Costly Features in Hierarchical Deep Sets
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.
Classification with Costly Features as a Sequential Decision-Making Problem
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.
Anomaly scores for generative models
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.
Approximation capability of neural networks on sets of probability measures and tree-structured data
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.
Are generative deep models for novelty detection truly better?
Many deep models have been recently proposed for anomaly detection.
Classification with Costly Features using Deep Reinforcement Learning
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.
Multiple Instance Learning for Malware Classification
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
