Model Detail
privacy-filter
—privacy-filter is a large language model with 700M parameters released by Open-OSS. The model is registered under the token-classification pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
privacy-filter ships with 700M parameters. Total weight footprint is approximately 1.4 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
privacy-filter is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models
arXiv:2607.13093v2 Announce Type: replace-cross Abstract: On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference i
Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks
arXiv:2607.14205v1 Announce Type: new Abstract: Federated learning (FL) enables multi-institutional training on clinical text without sharing raw data, but gradient inversion can reconstruct sensitive information from shared model updates. The extent of this leakage for radiology reports, and the ro
Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms
arXiv:2607.14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserv
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
arXiv:2607.13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-
Securing LLMs in the Wild: Privacy and Security Challenges at the Edge
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. While cloud deployments offer scalable compute, concerns over data sovereignty, complia
