arXiv Machine Learning July 31, 2026 By Cheng Wei (Honor Device Co., Ltd., Shenzhen, China)

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Read the original on arXiv Machine Learning →

arXiv:2607. 27940v1 Announce Type: new Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Jul 30

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint [1] (arXiv:2606.

llms fine-tuning safety

arXiv AI

Jun 15

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.

By Zixuan Gu, Xiaojun Ye, Yang Liu

llms fine-tuning benchmarks safety

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.

By Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree, Ihsen Alouani, Nael Abu-Ghazaleh

llms multimodal safety

arXiv AI

Jul 9

FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation

arXiv:2607. 07314v1 Announce Type: cross Abstract: Federated learning (FL) avoids explicit data exposure by keeping raw data on local clients, yet privacy risks remain in the training process and the learned model itself.

By Chongkai Li, Bang Zhang, Wenjian Luo

safety

arXiv AI

Aug 5

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels

arXiv:2608. 02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens.

By Yongwan Jo, Jinyoung Park, Euihyun Lee, Dokyung Song

llms efficiency

arXiv Machine Learning

Jul 7

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

arXiv:2412. 12640v2 Announce Type: replace Abstract: The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL).

By Rui Zhang, Ka-Ho Chow

llms safety

Related stories

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs

FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning