TRACE 攻击可从策略梯度重建智能体私有轨迹
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
发策略梯度也会泄露原始轨迹，这篇 TRACE 攻击 3-4.5ms 就能重建一帧，做联邦具身训练的得看看防御部分。
TRACE 是一种时序梯度反演攻击，能从每步策略学习梯度中自回归重建具身智能体的观测-动作序列。该攻击利用两个此前单帧方法忽略的结构信号：相邻时刻梯度间的跨时间相关性，以及在熵正则化足够小时从策略头梯度结构闭式恢复动作。在 held-out 具身场景上，TRACE 达到 18.8 dB PSNR，动作恢复接近完美，每帧重建耗时 3-4.5 ms，速度快于优化类攻击多个数量级。防御实验表明，仅靠设备端保留原始数据的联邦式训练不足以保护时序梯度流。
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
Distributed 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. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private observation-action trajectories from per-step policy-learning gradients. The attack exploits two structural signals ignored by prior single-frame methods: (i) cross-time correlation between successive embodied gradients, which we formalize via a conditional mutual-information bound, and (ii) closed-form action recovery from policy-head gradient structure, which we prove exact when standard entropy regularization is sufficiently small. On held-out embodied scenes, TRACE reaches $18.8$ dB PSNR with near-perfect action recovery at $3$-$4.5$ ms per reconstructed frame, dominating the learning-based baseline across all reconstruction metrics and exceeding optimization attacks while running orders of magnitude faster. Further evaluation demonstrates TRACE's broader applicability across recurrent, residual, and compact transformer victim architectures, multi-modal inputs, and larger discrete action spaces. Defense experiments suggest that protecting temporal gradient streams may require sequence-aware privacy mechanisms.
