Ideal cyber threat intelligence (CTI) includes insights into attacker strategies that are specific
to a network under observation. Such CTI currently requires extensive expert input for …

We present an algorithm for reconstruction of a probabilistic deterministic finite automaton
(PDFA) from a given black-box language model, such as a recurrent neural network (RNN) …

Obtaining the Earth-fixed coordinates is a fundamental requirement for long-distance
unmanned aerial vehicle (UAV) flight. Global navigation satellite systems (GNSSs) are the …

Data of sequential nature arise in many application domains in the form of, eg, textual data,
DNA sequences, and software execution traces. Different research disciplines have …

Understanding how a learned black box works is of crucial interest for the future of Machine
Learning. In this paper, we pioneer the question of the global interpretability of learned black …

Recombining known primitive concepts into larger novel combinations is a quintessentially
human cognitive capability. Whether large neural models in NLP can acquire this ability …

Finite state models, such as Mealy machines or state charts, are often used to express and
specify protocol and software behavior. Consequently, these models are often used in …

Attack graphs (AG) are used to assess pathways availed by cyber adversaries to penetrate a
network. State-of-the-art approaches for AG generation focus mostly on deriving …

Abstract Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in
learning and processing sequential data (eg, speech and natural language). However, due …

This article presents the content of the competition Transformers+\textsc {rnn}: Algorithms to
Yield Simple and Interpretable Representations (TAYSIR, the Arabic word for 'simple') …