Copertina

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xue, Lulu, Hu, Shengshan, Lu, Wei, Shen, Yan, Li, Dongxu, Guo, Peijin, Zhou, Ziqi, Li, Minghui, Zhang, Yanjun, Zhang, Leo Yu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
di: Xue, Lulu, et al.
Pubblicazione: (2025)

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

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)

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

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

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

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

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

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

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

UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
di: Pan, Hewen, et al.
Pubblicazione: (2025)

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

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

Verification of Machine Unlearning is Fragile
di: Zhang, Binchi, et al.
Pubblicazione: (2024)

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

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

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

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

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
di: Yan, Shihui, et al.
Pubblicazione: (2026)

Machine Unlearning for Streaming Forgetting
di: Shen, Shaofei, et al.
Pubblicazione: (2025)

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

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
di: Wang, Yichen, 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)

Machine Unlearning under Retain-Forget Entanglement
di: Cheng, Jingpu, et al.
Pubblicazione: (2026)

Don't Forget Too Much: Towards Machine Unlearning on Feature Level
di: Xu, Heng, 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)

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

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

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

DarkSAM: Fooling Segment Anything Model to Segment Nothing
di: Zhou, Ziqi, et al.
Pubblicazione: (2024)

Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning
di: Song, Qipeng, et al.
Pubblicazione: (2025)

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

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

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

When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation
di: Liang, Yiwen, et al.
Pubblicazione: (2025)

Forget and Explain: Transparent Verification of GNN Unlearning
di: Ahsan, Imran, et al.
Pubblicazione: (2025)

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

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

Towards Reliable Testing of Machine Unlearning
di: Mazhar, Anna, et al.
Pubblicazione: (2026)