Blog

2026

• Jul 03 A multiagent system for incident response planning

• May 08 The hidden work of an associate editor

• Jan 31 Digest of my PhD thesis

2025

• Dec 17 AI Slop

• Jul 22 My Erdős number

• May 08 Discussion forum for CSLE.

• Feb 10 CSLE v0.8.0

• Jan 13 The Univariate Kalman Filter

• Jan 09 Podcast about my thesis

2024

• Jun 07 CSLE v0.6.0

• Apr 08 Cauchy and Putin

• Mar 27 Policy Iteration as one step of Newton's method

• Mar 13 Installing CSLE

• Feb 21 A curated list of resources dedicated to reinforcement learning applied to cyber security.

2023

• Nov 29 Optimal Prediction in Partially Observed Linear Gaussian Systems

• Sep 09 CSLE v0.4.0

• May 30 Autonomous and artifically intelligent cyber defense agent

• May 27 Trends -- AI and security

• Jan 11 Reinforcement Learning Books

• Jan 03 The Need for Reinforcement Learning Research in Cyber Security

2022

• Oct 30 Reinforcement Learning for Automated Security

• Oct 13 Optimal Control for Climate Manipulation

• Aug 19 Structured Causal Models (SCMs) and MDPs

• Aug 11 Transform Analysis of Markov Processes.

• Jul 13 Data is the key.

• Jun 09 A software framework for building self-learning systems for cyber security.

• Mar 10 Reinforcement learning for cyber security

• Mar 04 The Partially Observed Markovian Optimal Stopping Problem

2021

• Dec 20 Towards a method for computing effective intrusion prevention policies using reinforcement learning

• Nov 01 The Uppsala Code and AI Ethics

• Aug 20 Friends don't let friends stop their learning curves

• Jul 09 An RCE Exploit for a Vulnerable Pengine Server

• Jun 16 A Time-to-Compromise Model of IDS Alerts and Login Attempts

2020

• May 06 Self-Play Non-Convergence in a Markov Game

• May 02 Expectation Maximization

• Mar 27 Is AI Good or Evil?

• Feb 16 Tesla P100 GPU Benchmark

2019

• May 11 Hello World