Adaptive Wizard for Removing Cross-Tier Misconfigurations in Active Directory
Authors: Huy Q. Ngo, Mingyu Guo, Hung X. Nguyen
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We verify the effectiveness of our algorithms on several synthetic AD graphs and an AD attack graph collected from a real organization. |
| Researcher Affiliation | Academia | 1The University of Adelaide EMAIL |
| Pseudocode | Yes | Algorithm 1 Adaptive Submodular Strategy (APP) Algorithm 2 Heuristics based on Exact Algorithm (DPR) |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. It mentions third-party tools like Blood Hound and Impro Hound, but not its own code release. |
| Open Datasets | No | The paper mentions synthetic AD attack graphs generated by ADSynth [Nguyen et al., 2024] and one real AD graph collected from a University. While ADSynth is a generator, no specific synthetic dataset used is provided, nor is the real AD graph made publicly available. |
| Dataset Splits | No | The paper mentions running trials (e.g., "16,000 trials", "200 trials") and evaluating on synthetic graphs (G1-G9, GS1-GS4) and one real AD graph (ORG). However, it does not specify any training/test/validation splits for these graphs or their underlying data. |
| Hardware Specification | Yes | All of the experiments are carried out on a highperformance computing cluster with 1 CPU and 24GB of RAM allocated to each trial. We allocated a100 GPUs for the training of RL agents. |
| Software Dependencies | No | The paper refers to algorithms like Proximal Policy Optimization (PPO) and Soft Actor Critic for Discrete Action (SAC) but does not provide specific version numbers for any software dependencies or libraries used in the implementation. |
| Experiment Setup | Yes | The budget constraint B is set at 10 for all experiments on synthetic graphs. For the real AD graph ORG, due to computing resource limitations, we report the average number of queries over 200 trials. Also for ORG, we reserve a higher budget of 20 and 30 queries due to the size of this graph, denoted ORG(20) and ORG(30) respectively. For the DPR algorithm, we set ̕ = 16 actions and a lookahead budget of B = 4 step. |