Copertina

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xue, Lulu, Hu, Shengshan, Qian, Linqiang, Guo, Peijin, Zhang, Yechao, Li, Minghui, Zhang, Yanjun, Ye, Dayong, Zhang, Leo Yu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
di: Xue, Lulu, et al.
Pubblicazione: (2025)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
di: Xue, Lulu, et al.
Pubblicazione: (2026)

Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning
di: Guo, Peijin, et al.
Pubblicazione: (2025)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
di: Zhang, Yechao, et al.
Pubblicazione: (2025)

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
di: Wang, Yichen, et al.
Pubblicazione: (2025)

Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
di: Wang, Xianlong, et al.
Pubblicazione: (2024)

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
di: Xue, Lulu, et al.
Pubblicazione: (2024)

DarkFed: A Data-Free Backdoor Attack in Federated Learning
di: Li, Minghui, et al.
Pubblicazione: (2024)

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
di: Zhou, Ziqi, et al.
Pubblicazione: (2024)

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
di: Zhang, Yechao, et al.
Pubblicazione: (2025)

Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
di: Ye, Dayong, et al.
Pubblicazione: (2025)

Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction
di: Guo, Peijin, et al.
Pubblicazione: (2025)

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
di: Zhang, Yechao, et al.
Pubblicazione: (2023)

Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
di: Zhang, Xiaomei, et al.
Pubblicazione: (2025)

BadRobot: Jailbreaking Embodied LLMs in the Physical World
di: Zhang, Hangtao, et al.
Pubblicazione: (2024)

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
di: Yu, Lei, et al.
Pubblicazione: (2025)

HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction
di: Li, Minghui, et al.
Pubblicazione: (2025)

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
di: Li, Minghui, et al.
Pubblicazione: (2025)

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
di: Mi, Di, et al.
Pubblicazione: (2024)

Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness
di: Song, Yufei, et al.
Pubblicazione: (2026)

SegTrans: Transferable Adversarial Examples for Segmentation Models
di: Song, Yufei, et al.
Pubblicazione: (2025)

Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
di: Xiao, Yaxin, et al.
Pubblicazione: (2025)

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
di: Wang, Xianlong, et al.
Pubblicazione: (2024)

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
di: Wang, Xianlong, et al.
Pubblicazione: (2024)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
di: Song, Yufei, et al.
Pubblicazione: (2024)

Transferable Adversarial Facial Images for Privacy Protection
di: Li, Minghui, et al.
Pubblicazione: (2024)

Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces
di: Shi, Junyu, et al.
Pubblicazione: (2025)

ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion
di: Li, Minghui, et al.
Pubblicazione: (2024)

Masked Language Model Based Textual Adversarial Example Detection
di: Zhang, Xiaomei, et al.
Pubblicazione: (2023)

DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
di: Zhou, Ziqi, et al.
Pubblicazione: (2025)

Real-Time Solar Radio Burst Detection with Machine Learning Trained on Physics-Based Synthetic Data
di: Zhang, Peijin
Pubblicazione: (2025)

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
di: Zhu, Zihui, et al.
Pubblicazione: (2026)

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
di: Xu, Heng, et al.
Pubblicazione: (2026)

Detecting and Corrupting Convolution-based Unlearnable Examples
di: Li, Minghui, et al.
Pubblicazione: (2023)

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
di: Hu, Hongsheng, et al.
Pubblicazione: (2024)

Test-Time Backdoor Detection for Object Detection Models
di: Zhang, Hangtao, et al.
Pubblicazione: (2025)

Large Language Model Watermark Stealing With Mixed Integer Programming
di: Zhang, Zhaoxi, et al.
Pubblicazione: (2024)

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
di: Naderloui, Nima, et al.
Pubblicazione: (2025)

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning
di: Zhang, Hangtao, et al.
Pubblicazione: (2023)

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
di: Zhang, Hangtao, et al.
Pubblicazione: (2024)