Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
TRACE reconstructs private embodied observation-action trajectories from policy gradients, reaching 18.8 dB PSNR.
TRACE is an amortized temporal gradient-inversion attack that autoregressively reconstructs private observation-action trajectories from per-step policy gradients in embodied reinforcement learning. It uses cross-time correlation between successive gradients and closed-form action recovery from policy-head gradients when entropy regularization is small. On held-out scenes it reaches 18.8 dB PSNR and near-perfect action recovery at 3–4.5 ms per frame, beating learning-based and optimization baselines. The attack extends to recurrent, residual, and compact transformer victims, multimodal inputs, and larger discrete action spaces.
- TRACE inverts temporal policy gradients to recover private observation-action trajectories.
- Held-out embodied scenes reach 18.8 dB PSNR with near-perfect action recovery.
- Each frame reconstructs in 3 to 4.5 milliseconds, faster than optimization attacks.
- Authors argue temporal gradient streams need sequence-aware privacy defenses.
- AI models
- TRACE
From the original article
1 min read at arxiv.orgDistributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks.
By Sudip Bhujel · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.