arXiv Machine Learning September 25, 2026 By Xuesong Wang, Mo Li, Xingyan Shi, Zhaoqian Liu, Shenghao Yang

Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack

Read the original on arXiv Machine Learning →

The paper introduces DiffSem, a diffusion-based approach for task‑oriented semantic communications that splits the diffusion process between transmitter‑side self‑noising and receiver‑side reverse denoising. It addresses privacy concerns by reducing model‑inversion attacks while preserving task accuracy, as demonstrated on MNIST, CIFAR‑10, and CelebA datasets. The method achieves higher task performance without enlarging transmitted feature size or increasing semantic leakage.

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.

arXiv Machine Learning

Jul 1

Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

arXiv:2606. 31973v1 Announce Type: cross Abstract: Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw data, enabling efficient and robust communication under resource and channel constraints.

By Yalin E. Sagduyu, Tugba Erpek, Aylin Yener, Sennur Ulukus

safety

arXiv Machine Learning

Aug 6

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.

By Zhicong Huang, Cheng Hong, Tao Wei

llms rag

arXiv Machine Learning

4d ago

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...

By Hadi Reisizadeh, Jiajun Ruan, Sijia Liu, Mingyi Hong

llms benchmarks safety

arXiv Computer Vision

Sep 21

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

The paper "Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses" provides a comprehensive review of model inversion (MI) attacks that exploit trained deep neural networks to reconstruct private training data. It traces the evolution of MI from early machine‑learning contexts to recent DNN‑based attacks across various modalities and learning tasks, offering a detailed taxonomy and comparative analysis of both attacks and defenses. The authors also present an open‑source toolbox on GitHub to support further research in this area.

By Hao Fang, Yixiang Qiu, Hongyao Yu, Wenbo Yu, Jiawei Kong, Baoli Chong, Bin Chen, Xuan Wang, Shu-Tao Xia, Ke Xu

safety

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 Machine Learning

Jul 31

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

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

By Cheng Wei (Honor Device Co., Ltd., Shenzhen, China)

llms fine-tuning safety

One email a morning, machine-written

Related stories

Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

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

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