LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud
It addresses privacy for users of cloud LLMs by enabling control over generated text, though it is incremental as it builds on existing cooperative frameworks.
The paper tackles the privacy issue in cloud-based LLM generation where servers control the process, proposing LatticeGen to hide generated text in a noised lattice, which protects over 50% of semantic content under strong attacks while degrading quality.
In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves. We propose LatticeGen, a cooperative framework in which the server still handles most of the computation while the user controls the sampling operation. The key idea is that the true generated sequence is mixed with noise tokens by the user and hidden in a noised lattice. Considering potential attacks from a hypothetically malicious server and how the user can defend against it, we propose the repeated beam-search attack and the mixing noise scheme. In our experiments we apply LatticeGen to protect both prompt and generation. It is shown that while the noised lattice degrades generation quality, LatticeGen successfully protects the true generation to a remarkable degree under strong attacks (more than 50% of the semantic remains hidden as measured by BERTScore).