Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference
It provides a principled, theoretically grounded defense for privacy-preserving collaborative LLM inference, addressing a critical security concern for edge-cloud deployments.
The paper proposes an information-theoretic defense against prompt inversion attacks in collaborative LLM inference, achieving up to 35% reduction in attack success while maintaining utility and latency constraints.
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.