Learning Models of Adversarial Agent Behavior under Partial
Observability
- URL: http://arxiv.org/abs/2306.11168v2
- Date: Wed, 5 Jul 2023 16:07:24 GMT
- Title: Learning Models of Adversarial Agent Behavior under Partial
Observability
- Authors: Sean Ye, Manisha Natarajan, Zixuan Wu, Rohan Paleja, Letian Chen, and
Matthew C. Gombolay
- Abstract summary: We present Graph based Adversarial Modeling with Mutal Information (GrAMMI) for modeling the behavior of an adversarial opponent agent.
GrAMMI is a novel graph neural network (GNN) based approach that uses mutual information as an auxiliary objective.
- Score: 6.757727645540147
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The need for opponent modeling and tracking arises in several real-world
scenarios, such as professional sports, video game design, and drug-trafficking
interdiction. In this work, we present Graph based Adversarial Modeling with
Mutal Information (GrAMMI) for modeling the behavior of an adversarial opponent
agent. GrAMMI is a novel graph neural network (GNN) based approach that uses
mutual information maximization as an auxiliary objective to predict the
current and future states of an adversarial opponent with partial
observability. To evaluate GrAMMI, we design two large-scale, pursuit-evasion
domains inspired by real-world scenarios, where a team of heterogeneous agents
is tasked with tracking and interdicting a single adversarial agent, and the
adversarial agent must evade detection while achieving its own objectives. With
the mutual information formulation, GrAMMI outperforms all baselines in both
domains and achieves 31.68% higher log-likelihood on average for future
adversarial state predictions across both domains.
Related papers
- MAP-Former: Multi-Agent-Pair Gaussian Joint Prediction [6.110153599741102]
There is a gap in risk assessment of trajectories between the trajectory information coming from a traffic motion prediction module and what is actually needed.
Existing prediction models yield joint predictions of agents' future trajectories with uncertainty weights or marginal Gaussian probability density functions (PDFs) for single agents.
This paper introduces a novel approach to motion prediction, focusing on predicting agent-pair covariance matrices in a scene-centric'' manner.
arXiv Detail & Related papers (2024-04-30T06:21:42Z) - Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks [8.06071340190569]
Black-box machine learning (ML) models can be exploited to carry out privacy threats such as membership inference attacks (MIA)
Existing works have only analyzed MIA in a single "what if" interaction scenario between an adversary and the target ML model.
We propose a sound mathematical formulation to prove that such an optimal threshold exists, which can be used to launch MIA.
arXiv Detail & Related papers (2024-04-10T16:14:05Z) - Interactive Autonomous Navigation with Internal State Inference and
Interactivity Estimation [58.21683603243387]
We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework.
These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents.
Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
arXiv Detail & Related papers (2023-11-27T18:57:42Z) - Diffusion Models for Multi-target Adversarial Tracking [0.49157446832511503]
Target tracking plays a crucial role in real-world scenarios, particularly in drug-trafficking interdiction.
As unmanned drones proliferate, accurate autonomous target estimation is even more crucial for security and safety.
This paper presents Constrained Agent-based Diffusion for Enhanced Multi-Agent Tracking (CADENCE), an approach aimed at generating comprehensive predictions of adversary locations.
arXiv Detail & Related papers (2023-07-12T15:34:39Z) - Decentralized Adversarial Training over Graphs [55.28669771020857]
The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years.
This work studies adversarial training over graphs, where individual agents are subjected to varied strength perturbation space.
arXiv Detail & Related papers (2023-03-23T15:05:16Z) - Targeted Adversarial Attacks against Neural Network Trajectory
Predictors [14.834932672948698]
Trajectory prediction is an integral component of modern autonomous systems.
Deep neural network (DNN) models are often employed for trajectory forecasting tasks.
We propose a targeted adversarial attack against DNN models for trajectory forecasting tasks.
arXiv Detail & Related papers (2022-12-08T08:34:28Z) - AdvDO: Realistic Adversarial Attacks for Trajectory Prediction [87.96767885419423]
Trajectory prediction is essential for autonomous vehicles to plan correct and safe driving behaviors.
We devise an optimization-based adversarial attack framework to generate realistic adversarial trajectories.
Our attack can lead an AV to drive off road or collide into other vehicles in simulation.
arXiv Detail & Related papers (2022-09-19T03:34:59Z) - Deep Interactive Motion Prediction and Planning: Playing Games with
Motion Prediction Models [162.21629604674388]
This work presents a game-theoretic Model Predictive Controller (MPC) that uses a novel interactive multi-agent neural network policy as part of its predictive model.
Fundamental to the success of our method is the design of a novel multi-agent policy network that can steer a vehicle given the state of the surrounding agents and the map information.
arXiv Detail & Related papers (2022-04-05T17:58:18Z) - Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction
and Tracking [23.608125748229174]
We propose a generic generative neural system for multi-agent trajectory prediction involving heterogeneous agents.
The proposed system is evaluated on three public benchmark datasets for trajectory prediction.
arXiv Detail & Related papers (2021-02-18T02:25:35Z) - Traffic Agent Trajectory Prediction Using Social Convolution and
Attention Mechanism [57.68557165836806]
We propose a model to predict the trajectories of target agents around an autonomous vehicle.
We encode the target agent history trajectories as an attention mask and construct a social map to encode the interactive relationship between the target agent and its surrounding agents.
To verify the effectiveness of our method, we widely compare with several methods on a public dataset, achieving a 20% error decrease.
arXiv Detail & Related papers (2020-07-06T03:48:08Z) - Graph Backdoor [53.70971502299977]
We present GTA, the first backdoor attack on graph neural networks (GNNs)
GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features.
It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
arXiv Detail & Related papers (2020-06-21T19:45:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.