Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
cs.LG
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/mit-han-lab/dlg
Terminology
Sources
- ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
- Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
- Differentially Private Federated Learning: A Client Level Perspective
- Gradient Inversion in Federated Reinforcement Learning
- AI2-THOR: An Interactive 3D Environment for Visual AI
- SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
- Sequence Level Training with Recurrent Neural Networks
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
- Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
- CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
- iDLG: Improved Deep Leakage from Gradients
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks