{"slug": "temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied", "title": "Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning", "summary": "A 24 Sep 2026 arXiv paper introduces TRACE (Temporal Reconstruction Attack on Consecutive Encodings), an amortized temporal gradient-inversion attack that autoregressively reconstructs private observation-action trajectories from per-step policy-learning gradients in distributed embodied reinforcement learning. On held-out embodied scenes, TRACE reaches 18.8 dB PSNR with near-perfect action recovery at 3–4.5 ms per reconstructed frame, outperforming the learning-based baseline on all reconstruction metrics and running orders of magnitude faster than optimization attacks. The authors report the attack generalizes across recurrent, residual and compact transformer victim architectures, multi-modal inputs and larger discrete action spaces, and conclude that protecting temporal gradient streams may require sequence-aware privacy mechanisms.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 24 Sep 2026]\n\n# Title:Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning\n\n[View PDF](http://arxiv.org/pdf/2609.30258v1)\n\n[HTML (experimental)](https://arxiv.org/html/2609.30258v1)\n\nAbstract: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.\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied", "canonical_source": "http://arxiv.org/abs/2609.30258v1", "published_at": "2026-09-25 16:46:12+00:00", "updated_at": "2026-09-25 17:00:09.664301+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "ai-safety", "robotics", "artificial-intelligence"], "entities": ["TRACE", "arXiv", "Temporal Reconstruction Attack on Consecutive Encodings"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied", "markdown": "https://wpnews.pro/news/temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied.md", "text": "https://wpnews.pro/news/temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied.txt", "jsonld": "https://wpnews.pro/news/temporal-gradient-inversion-for-private-trajectory-reconstruction-in-embodied.jsonld"}}