← Back to all news
arXiv Machine Learning By Georgios Politis, Evangelos Pappas

Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys

Read the original on arXiv Machine Learning →

The paper reports a privacy breach in a two-node split‑LLM training system where the returned gradient reveals which data rows were real, despite the system passing standard privacy checks. By exploiting the fact that decoy rows produce zero gradients, an attacker can identify real rows with 100% accuracy across multiple runs. The authors demonstrate that adding gradient clipping and noise can mitigate the leak, but the system remains vulnerable to several untested attack vectors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 16

Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning

The paper investigates privacy and integrity risks in federated fine‑tuning of a pretrained MobileNetV4 model on Quick, Draw! data. It shows that a single client update can reveal private labels, that label‑count recovery degrades with more clients, and that backdoor and label‑flipping attacks can succeed under FedAvg but are mitigated by FLTrust. The study also demonstrates a live poisoning session using Indigma’s FedMaestro orchestrator.

By Vasileios Perifanis, Nikolaos Pavlidis
fine-tuningmultimodalsafety
More like this →
arXiv Machine Learning
Oct 8

HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption

HE‑OFT is a cryptographically secure one‑shot federated fine‑tuning protocol that protects privacy by exchanging only one encrypted contribution and never revealing the trained model. Each client fine‑tunes a low‑rank adapter and a classifier head on a frozen public backbone, keeps the adapter, and uploads an encrypted head displacement that the server combines using multiparty CKKS without decryption. On four text classification tasks and one vision task, HE‑OFT achieves 61–79 % accuracy, retaining 85–96 % of the accuracy of a disclosed model, while a test‑time query takes 443.1–1713.1 s on one core or 56.1–255.1 s on a GPU, with level restoration reducing traffic from 1.6 GiB to 13.5 MiB.

By Halil \.Ibrahim Kanpak, Sinem Sav, Alptekin K\"up\c{c}\"u
nlpfine-tuningsafety
More like this →