Related papers: Proceedings First International Workshop on Graphi…
Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on…
This volume contains the proceedings of the Combined 19th International Workshop on Expressiveness in Concurrency and the 9th Workshop on Structural Operational Semantics (EXPRESS/SOS 2012), which took place on 3rd September 2012 in…
MEMICS provides a forum for doctoral students interested in applications of mathematical and engineering methods in computer science. Besides a rich technical programme (including invited talks, regular papers, and presentations), MEMICS…
In this paper we describe our experience in designing and evaluating our graduate level computer security seminar course. In particular, our seminar is designed with two goals in mind. First, to instil critical thinking by teaching graduate…
This volume contains the proceedings of the Ninth Workshop on Mathematically Structured Functional Programming (MSFP 2022). The meeting took place on the 2nd of April as a satellite of European Joint Conferences on Theory & Practice of…
Grasping of diverse objects in unstructured environments remains a significant challenge. Open-loop grasping methods, effective in controlled settings, struggle in cluttered environments. Grasp prediction errors and object pose changes…
This volume contains the proceedings of EXPRESS/SOS 2019: the Combined 26th International Workshop on Expressiveness in Concurrency and the 16th Workshop on Structural Operational Semantics, which was held on August 26, 2019, in Amsterdam…
This volume contains the revised versions of papers presented at the Fourth International Workshop on Verification and Program Transformation (VPT 2016) on April 2, 2016 in Eindhoven, The Netherlands. The workshop is an event of the…
The software development process is considered as one of the key guidelines in the creation of said software and this approach is necessary for providing a more efficient yet satisfactory output. Without separation of work into distinct…
Advanced cyber threats (e.g., Fileless Malware and Advanced Persistent Threat (APT)) have driven the adoption of provenance-based security solutions. These solutions employ Machine Learning (ML) models for behavioral modeling and critical…
This volume contains the joint proceedings of the Workshop on Games for the Synthesis of Complex Systems (CASSTING'16) and of the 3rd International Workshop on Synthesis of Complex Parameters (SynCoP'16). The workshops were held in…
Security attacks are hard to understand, often expressed with unfriendly and limited details, making it difficult for security experts and for security analysts to create intelligible security specifications. For instance, to explain Why…
Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks (GNNs) have shown promise in this domain by modeling rich structural…
Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many of these models prioritize high utility performance, such as…
The increasingly concurrent and parallel landscape of hardware and software infrastructures demands the exploration and understanding of a wide variety of foundational and practical ideas. The International Workshop on Programming Language…
Modern hardware platforms, from the very small to the very large, increasingly provide parallel and distributed computing resources for applications to maximise performance. Many applications therefore need to make effective use of tens,…
We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational…
Software engineers are faced with the challenge of creating control algorithms for increasingly complex dynamic systems, such as the management of communication network topologies. To support rapid prototyping for these increasingly complex…
Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate…
As cybersecurity threats continue to evolve, the need for advanced tools to analyze and understand complex cyber environments has become increasingly critical. Graph theory offers a powerful framework for modeling relationships within cyber…