Image de couverture de livre

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fu, Shaopeng, Sun, Xuexue, Qing, Ke, Zheng, Tianhang, Wang, Di
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning 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

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
par: Zhang, Yechao, et autres
Publié: (2025)

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
par: Han, Tingxu, et autres
Publié: (2024)

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory
par: Fu, Shaopeng, et autres
Publié: (2026)

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
par: Fu, Shaopeng, et autres
Publié: (2025)

FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
par: Zheng, Tianhang, et autres
Publié: (2024)

DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders
par: Hou, Sizai, et autres
Publié: (2024)

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks
par: Luo, Jiayi, et autres
Publié: (2025)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
par: Wen, Yuxin, et autres
Publié: (2024)

How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
par: Liu, Meiqi, et autres
Publié: (2025)

Twin Auto-Encoder Model for Learning Separable Representation in Cyberattack Detection
par: Dinh, Phai Vu, et autres
Publié: (2024)

A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference
par: Kumar, Abhinav, et autres
Publié: (2023)

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
par: Ding, Ruyi, et autres
Publié: (2024)

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
par: Jin, Huitong, et autres
Publié: (2024)

Mitigating Downstream Model Risks via Model Provenance
par: Wang, Keyu, et autres
Publié: (2024)

Mitigating Error Amplification in Fast Adversarial Training
par: Zhao, Mengnan, et autres
Publié: (2026)

Selective Pre-training for Private Fine-tuning
par: Yu, Da, et autres
Publié: (2023)

Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
par: Zhao, Xiangyu, et autres
Publié: (2024)

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
par: Naderloui, Nima, et autres
Publié: (2025)

Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classification
par: Li, Yujie, et autres
Publié: (2024)

MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference
par: Wang, Yongqin, et autres
Publié: (2022)

Attacking Attention of Foundation Models Disrupts Downstream Tasks
par: Silva, Hondamunige Prasanna, et autres
Publié: (2025)

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
par: Jiang, Yongqi, et autres
Publié: (2026)

Pre-training Differentially Private Models with Limited Public Data
par: Bu, Zhiqi, et autres
Publié: (2024)

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
par: Lu, Yiwei, et autres
Publié: (2024)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
par: Zhang, Jinghuai, et autres
Publié: (2022)

Training Large ASR Encoders with Differential Privacy
par: Chauhan, Geeticka, et autres
Publié: (2024)

Multiple-Input Auto-Encoder Guided Feature Selection for IoT Intrusion Detection Systems
par: Dinh, Phai Vu, et autres
Publié: (2024)

MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
par: Fu, Wenjie, et autres
Publié: (2024)

Machine Unlearning of Pre-trained Large Language Models
par: Yao, Jin, et autres
Publié: (2024)

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
par: Wu, Shuchi, et autres
Publié: (2023)

Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
par: Anand, Saurabh, et autres
Publié: (2026)

Accuracy Improvement in Differentially Private Logistic Regression: A Pre-training Approach
par: Hoseinpour, Mohammad, et autres
Publié: (2023)

SecEncoder: Logs are All You Need in Security
par: Bulut, Muhammed Fatih, et autres
Publié: (2024)

Learning to Poison Large Language Models for Downstream Manipulation
par: Zhou, Xiangyu, et autres
Publié: (2024)

FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation
par: Gu, Yuechun, et autres
Publié: (2024)

On the (In)Security of Loading Machine Learning Models
par: Digregorio, Gabriele, et autres
Publié: (2025)

Privacy-Preserving Verifiable Neural Network Inference Service
par: Riasi, Arman, et autres
Publié: (2024)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
par: Zhao, Mengnan, et autres
Publié: (2026)

DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
par: Wu, Huiwen, et autres
Publié: (2024)

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud
par: Duan, Shijin, et autres
Publié: (2024)