Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning
cs.LG, cs.MA
Submitted: 2025-08-12
Updated: 2026-11-03
Code: https://github.com/AmineAndam04/black-box-marl
Terminology
Sources
- CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
- Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation
- Explaining and Harnessing Adversarial Examples
- Sparse Adversarial Attack in Multi-agent Reinforcement Learning
- Adversarial Attacks on Neural Network Policies
- Delving into adversarial attacks on deep policies
- Neural Recursive Belief States in Multi-Agent Reinforcement Learning
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Intriguing properties of neural networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis