arXiv AI
Privacy-preserving inference on hosted models: a learned input-embedding transform for frozen Qwen3.8-27B
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 21
Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
arXiv:2310. 16152v5 Announce Type: replace-cross Abstract: Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis.
arXiv AI
Jun 4
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
arXiv Machine Learning
Jun 16
Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference
arXiv:2606. 16461v1 Announce Type: new Abstract: Running large language models locally is often impractical, pushing inference on sensitive text to third-party providers.
arXiv AI
Aug 17
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
arXiv:2608. 14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices.
arXiv Machine Learning
Jun 17
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
arXiv AI
Sep 15
Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models
arXiv:2609.15671v1 Announce Type: cross Abstract: Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Fede...