2026

[Demo] Multiagent Incident Response Planning with Code Models; demonstration of our multiagent incident response system. Video

[IEEE TCSP] Autonomous Security Management of Networked Systems through Learning-based Control; IEEE CSS TCSP symposium, Paris, France. Video

[NDSS] Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination; NDSS, San Diego, USA. Video Video (talk recording)

[AAAI] Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees; AAAI, Singapore. Video

2025

[Demo] Incident response planning demonstration for NDSS 2026. Video

[City University of Hong Kong] Automated Security with a Foundation Model; City University of Hong Kong. Video

[Demo] Video demonstration of our LLM-based incident response system. Video

[Podcast] Podcasts about our LLM-based incident response system. Video Video

[Demo] Demo of our LLM-based incident response system. Video

[Ericsson Research] Online Identification of IT Systems through Active Causal Learning; Ericsson Research, Melbourne, Australia. Video

[ASU] Approximation in Value Space using Aggregation, with Applications to POMDPs and Cybersecurity; guest lecture at Arizona State University. Video

[ASU] Aggregation Methods for Approximating POMDPs; lecture at Arizona State University. Video

[Demo] Solving the Rocksample POMDP with Belief Aggregation and Dynamic Programming. Video

[KTH] Adaptive Security Policies via Belief Aggregation and Rollout; NetCon group, KTH. Video

2024

[PhD defense] Optimal Security Response to Network Intrusions in IT Systems; Ph.D. defense at KTH. Video

[University of Melbourne] Intrusion Tolerance as a Two-Level Game; University of Melbourne, Australia. Video

[CDIS] Automated Intrusion Response; CDIS Spring Conference, Stockholm. Video Video (KTH Play)

[Demo] Installation of the Cyber Security Learning Environment (CSLE) v0.5. Video

[NSE seminar] Automated Security Response through Online Learning with Adaptive Conjectures; NSE seminar, KTH. Video

2023

[MIT] Learning Near-Optimal Intrusion Response for Large-Scale IT Infrastructures via Decomposition; MIT, Boston, USA. Video

[Demo] The Cyber Security Learning Environment (CSLE) v0.2.0. Video

[Ericsson Research] Learning Automated Intrusion Response; Ericsson Research, Stockholm. Video

[NOMS] Digital Twins for Security Automation; NOMS, Miami, USA. Video

[NOMS] Demonstrating a System for Dynamically Meeting Management Objectives on a Service Mesh; NOMS, Miami, USA. Video

[NYU] Intrusion Response through Optimal Stopping; invited talk at New York University. Video

2022

[IT-försvarsdagen] Självlärande system för cyberförsvar; IT-försvarsdagen, Linköping. Video Video (recording)

[CDIS] Självlärande system för cyberförsvar. Video

[Demo] Dynamically meeting performance objectives for multiple services on a service mesh; Shahab and Stadler. Video

[CNSM] An Online Framework for Adapting Security Policies in Dynamic IT Environments; CNSM, Thessaloniki, Greece. Video

[CDIS] Self-learning Systems for Cyber Defense; CDIS fall retreat, Lidingö. Video

[ICML] Learning Security Strategies through Game Play and Optimal Stopping; ML4Cyber workshop at ICML, Baltimore, USA. Video

[NOMS] A System for Interactive Examination of Learned Security Policies (best demonstration award); NOMS, Budapest, Hungary. Video Video (short version)

2021

[CNSM] Learning Intrusion Prevention Policies through Optimal Stopping; CNSM, Izmir, Turkey. Video

[CDIS] Self-Learning Systems for Cyber Defense; Stockholm. Video

2020

[CNSM] Finding Effective Security Strategies through Reinforcement Learning and Self-Play; CNSM, Izmir, Turkey. Video

2019

[Spark+AI Summit] End-to-End ML Pipelines with Databricks Delta and Hopsworks Feature Store; Spark+AI Summit, Amsterdam. Video

[SF ML Meetup] Distributed Deep Learning with Hopsworks; SF Machine Learning Meetup, San Francisco. Video

[FOSDEM] Feature Store: the missing data layer in ML pipelines; FOSDEM, Brussels. Video

2018

[MSc defense] Deep Text Mining of Instagram Data Without Strong Supervision; M.Sc. thesis defense at KTH. Video

•