Abstract:Automated cyber defense (ACD) seeks to protect computer networks with minimal or no human intervention, reacting to intrusions by taking corrective actions such as isolating hosts, resetting services, deploying decoys, or updating access controls. However, existing approaches for ACD, such as deep reinforcement learning (RL), often face difficult exploration in complex networks with large decision/state spaces and thus require an expensive amount of samples. Inspired by the need to learn sample-efficient defense policies, we frame ACD in CAGE Challenge 4 (CAGE-4 / CC4) as a context-based partially observable Markov decision problem and propose a planning-centric defense policy based on Monte Carlo Tree Search (MCTS). It explicitly models the exploration-exploitation tradeoff in ACD and uses statistical sampling to guide exploration and decision making. We make novel use of graph neural networks (GNNs) to embed observations from the network as attributed graphs, to enable permutation-invariant reasoning over hosts and their relationships. To make our solution practical in complex search spaces, we guide MCTS with learned graph embeddings and priors over graph-edit actions, combining model-free generalization and policy distillation with look-ahead planning. We evaluate the resulting agent on CC4 scenarios involving diverse network structures and adversary behaviors, and show that our search-guided, graph-embedding-based planning improves defense reward and robustness relative to state-of-the-art RL baselines.




Abstract:We studied a target tracking algorithm based on millimeter-wave (MMW) radar in an autonomous driving environment. Aiming at the cluster matching in the target tracking stage, a new weighted feature similarity algorithm is proposed, which increases the matching rate of the same target in adjacent frames under strong environmental noise and multiple interference targets. For autonomous driving scenarios, we constructed a method that uses its motion parameters to extract and correct the trajectory of a moving target, which solves the problem of moving target detection and trajectory correction during vehicle movement. Finally, the feasibility of the proposed method was verified by a series of experiments in autonomous driving environments. The results verify the high recognition accuracy and low positional error of the method.