arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.
arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...
arXiv:2608. 04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate.
arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.
Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service p...
arXiv:2606. 04069v1 Announce Type: cross Abstract: Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sampling.
arXiv:2606. 16461v1 Announce Type: new Abstract: Running large language models locally is often impractical, pushing inference on sensitive text to third-party providers.
The paper introduces PriCoder, a method for teaching large language models (LLMs) to effectively use private library APIs for code generation. PriCoder synthesizes training data by constructing a graph and applying two operators—Progressive Graph Evolution to increase diversity and Multidimensional Graph Pruning to enhance quality. Experiments on three mainstream LLMs demonstrate that PriCoder boosts private‑library code generation by over 20% in pass@1, while leaving general code generation largely unchanged.
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
arXiv:2606. 26664v1 Announce Type: cross Abstract: Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs.
arXiv:2606. 26396v1 Announce Type: new Abstract: Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data.