Image de couverture de livre

Analyzing Inference Privacy Risks Through Gradients in Machine Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Zhuohang, Lowy, Andrew, Liu, Jing, Koike-Akino, Toshiaki, Parsons, Kieran, Malin, Bradley, Wang, Ye
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploring User-level Gradient Inversion with a Diffusion Prior
par: Li, Zhuohang, et autres
Publié: (2024)

Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
par: Lowy, Andrew, et autres
Publié: (2024)

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
par: Hase, Ryo, et autres
Publié: (2024)

Efficient Differentially Private Fine-Tuning of Diffusion Models
par: Liu, Jing, et autres
Publié: (2024)

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
par: Rashid, Md Rafi Ur, et autres
Publié: (2024)

Directional Embedding Smoothing for Robust Vision Language Models
par: Wang, Ye, et autres
Publié: (2026)

Smoothed Embeddings for Robust Language Models
par: Hase, Ryo, et autres
Publié: (2025)

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
par: Khattar, Vanshaj, et autres
Publié: (2026)

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
par: Yoon, Jeongho, et autres
Publié: (2026)

Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning
par: Díaz, Judith Sáinz-Pardo, et autres
Publié: (2026)

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
par: Ozturk, Ozer, et autres
Publié: (2025)

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
par: Zeng, Ziqian, et autres
Publié: (2024)

Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)
par: Lin, Yu, et autres
Publié: (2026)

A Consensus Privacy Metrics Framework for Synthetic Data
par: Pilgram, Lisa, et autres
Publié: (2025)

Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
par: Yu, Honglan, et autres
Publié: (2025)

MedHE: Communication-Efficient Privacy-Preserving Federated Learning with Adaptive Gradient Sparsification for Healthcare
par: Yesmin, Farjana
Publié: (2025)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
par: Luo, Zhifan, et autres
Publié: (2025)

AutoHLS: Learning to Accelerate Design Space Exploration for HLS Designs
par: Ahmed, Md Rubel, et autres
Publié: (2024)

No Free Lunch Theorem for Privacy-Preserving LLM Inference
par: Zhang, Xiaojin, et autres
Publié: (2024)

Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks
par: Fu, Haowei, et autres
Publié: (2025)

Unveiling Privacy Risks in LLM Agent Memory
par: Wang, Bo, et autres
Publié: (2025)

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey
par: Zhang, Chaoyu, et autres
Publié: (2024)

Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning
par: Li, Qi, et autres
Publié: (2024)

When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning
par: Sun, Ruining, et autres
Publié: (2025)

Explainable Machine Learning-Based Security and Privacy Protection Framework for Internet of Medical Things Systems
par: Si-ahmed, Ayoub, et autres
Publié: (2024)

Robust Privacy: Inference-Time Privacy through Certified Robustness
par: Jin, Jiankai, et autres
Publié: (2026)

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
par: Ye, Pukang, et autres
Publié: (2025)

MASCOT: Analyzing Malware Evolution Through A Well-Curated Source Code Dataset
par: Li, Bojing, et autres
Publié: (2025)

Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption
par: Ye, Huanyi, et autres
Publié: (2026)

Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
par: Wang, Haodi, et autres
Publié: (2024)

Detecting Quishing Attacks with Machine Learning Techniques Through QR Code Analysis
par: Trad, Fouad, et autres
Publié: (2025)

VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices
par: Zhang, Han, et autres
Publié: (2024)

Unveiling Privacy Policy Complexity: An Exploratory Study Using Graph Mining, Machine Learning, and Natural Language Processing
par: Ramasamy, Vijayalakshmi, et autres
Publié: (2025)

Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives
par: Zeng, Wenxuan, et autres
Publié: (2025)

ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach
par: Hu, Yuke, et autres
Publié: (2023)

Bridging Privacy and Robustness for Trustworthy Machine Learning
par: Zhang, Xiaojin, et autres
Publié: (2024)

Footprints of Data in a Classifier: Understanding the Privacy Risks and Solution Strategies
par: Sadhukhan, Payel, et autres
Publié: (2024)

Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach
par: Yang, Hua, et autres
Publié: (2025)

Design and Optimization of Cloud Native Homomorphic Encryption Workflows for Privacy-Preserving ML Inference
par: Bollikonda, Tejaswini
Publié: (2025)

EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference
par: Park, Jaewoo, et autres
Publié: (2025)