Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference

Computer Science > Cryptography and Security [Submitted on 10 Jun 2026] Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference Sayedeh Leila Noorbakhsh, Hossein Khalili, Nader Sehatbakhsh Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers. However, transmitting intermediate activations exposes sensitive user prompts to prompt inversion attacks, where an adversary reconstructs the original input from shared representations. Existing defenses rely largely on heuristic perturbations or empirical tuning, offering limited theoretical understanding of privacy leakage and its interaction with utility and latency constraints. We propose an information-theoretic defense framework for prompt inversion in collaborative LLM inference. Our approach learns privacy-preserving representations by explicitly minimizing the mutual information between intermediate activations and the input prompt while maintaining task utility under computational constraints. We derive theoretical guarantees on prompt reconstruction error, characterize fundamental privacy-utility tradeoffs, and establish token-level accuracy bounds for downstream inference. We then propose a novel defense based on privacy adapters implemented via low-dimensional information bottlenecks. Extensive experiments across multiple settings demonstrate that our method achieves superior privacy-utility-latency tradeoffs compared to existing defenses (up to 35% reduction in attack success), providing a principled foundation for private and efficient collaborative LLM inference. Comments: Preprint. 33 pages, 5 figures Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.11592 [cs.CR]   (or arXiv:2606.11592v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.11592 Focus to learn more Submission history From: Nader Sehatbakhsh [view email] [v1] Wed, 10 Jun 2026 02:36:26 UTC (198 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 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?)