Artifacts
2026
[Causal Controlled Degradation (CCD)] A Python library for cyber resilience through controlled degradation. Data repository.
[A multiagent incident response system] A multiagent incident response system that autonomously investigates security incidents and recommends optimized response actions. Video demonstration.
[5G Cloud RAN measurements] A novel dataset comprising 168 hours of monitoring data collected from our 5G testbed..
2025
[SAB.jl] A Julia package implementing an aggregation method for value approximation of one-sided partially observed stochastic games (OS-POSGs); artifacts related to the paper “Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees”, published at AAAI 2026.
[Code and data for incident response LLM fine-tuning] Artifacts related to the paper “Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination”, which is accepted to The Network and Distributed System Security (NDSS) Symposium 2026. We introduce a novel method that enables the effective use of a large language model (LLM) to provide decision support for incident response planning. Data repository; Video demonstration.
2021
[awesome-rl-for-cybersecurity] A curated list of resources dedicated to reinforcement learning applied to cyber security..
[gym-optimal-intrusion-response] A reinforcement learning environment for simulating attack and defense operations in an optimal stopping game..
2020
[The Cyber Security Learning Environment (CSLE)] CSLE is a framework for evaluating and developing reinforcement learning agents for control problems in cyber security. Everything from network emulation, to simulation, and learning in CSLE have been co-designed to provide an environment where it is possible to train and evaluate reinforcement learning agents for practical cyber security tasks. Documentation.
[gym-idsgame] A reinforcement learning environment for simulating attack and defense operations in an abstract network intrusion Markov game..
2018
[Hopsworks] Hopsworks is a platform for horizontally scalable deep learning pipelines on top of Hadoop. Blog.
[FastTextOnSpark] An implementation of the FastText algorithm for training word embeddings that runs on Spark, the first distributed implementation in the world..
[SemWebTutorial] Semantic Web Tutorial. Report.
2017
[Hops-util-py] A python library for deep learning and data processing..
[MLFD] Implementation of a next-generation failure detector for distributed systems with provable strong completeness, using a machine learning model updated with streaming data to detect machine failures. Report.
[FashionRec] Implementation in Tensorflow of a multi-class multi-label text classification model using probabilistic labels learned from weak supervision and support for pre-trained word embeddings..
[Erlang Pengine] A distributed erlang client to a prolog pengine server. It enables you to run first-order logic programs and constraint programming programs from Erlang..
[Distributed Linearizable Key-Value Store] Implementation of a provable linearizable key-value store using virtually synchronous group communication and passive replication. Report.
[Logoot-Undo4J] Java implementation of CRDT for Logoot-Undo: Distributed Collaborative Editing System on P2P networks. Report.
[Advent Of Code 2016 in Prolog] Implementation of the Advent of Code series of challenges year 2016 in Prolog..
[DataMining] Implementation of various data mining algorithms. Report.
2016
[SSL VPN] A C implementation of a SSL VPN that supports secure key exchange and encrypted communication..
[AgentProgramming] Programming of Multi-Agent Systems. Report 1; Report 2.
