Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference

Computer Science > Cryptography and Security [Submitted on 2 Aug 2026] Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference Shuaifan Jin, Zhibo Wang, Qiyuan Wang, Yiting Han, Yajie Zhou, Yuanfan Zhang, Jiahui Hu, Xiaoyi Pang Collaborative inference deploys Large Vision-Language Models (LVLMs) by partitioning computation between edge devices and the cloud. While withholding raw inputs supposedly ensures privacy, transmitting intermediate hidden states exposes a critical attack surface. However, it remains unclear whether deep-layer LVLM hidden states retain recoverable private information, given that visual content has been projected into the language embedding space. To address this concern, we theoretically analyze LVLM hidden-state recoverability and show that, under regularity assumptions and a positive semantic--nuisance margin, privacy-relevant visual semantics remain identifiable and stably recoverable. Motivated by this analysis, we propose RASR, a novel coarse-to-fine multimodal reconstruction attack. RASR obtains initial image and text reconstructions through modality-specific inverse paths that follow their respective forward processing pipelines in reverse, and then uses hidden-state consistency to refine both reconstructions. Evaluations on Qwen3-VL-8B-Instruct and LLaVA-1.5-7B across five datasets demonstrate that RASR reduces image reconstruction MSE by \(\sim\)50\% compared to the strongest baselines, while achieving up to 99\% token accuracy for text recovery. These results show that privacy-sensitive visual and textual information can be recovered even from deep-layer LVLM hidden states, exposing the privacy risks of collaborative inference. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2608.01020 [cs.CR]   (or arXiv:2608.01020v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.01020 Focus to learn more Submission history From: Shuaifan Jin [view email] [v1] Sun, 2 Aug 2026 05:56:23 UTC (13,784 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)