Imagen de Portada

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sui, Zhihao, Hu, Liang, Cao, Jian, Liu, Dora D., Naseem, Usman, Lai, Zhongyuan, Zhang, Qi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
por: Fu, Jie, et al.
Publicado: (2026)

COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement
por: Sui, Zhihao, et al.
Publicado: (2025)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
por: Xue, Jing, et al.
Publicado: (2025)

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

When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
por: Hu, Ruihan, et al.
Publicado: (2026)

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage
por: Hmida, Firas Ben, et al.
Publicado: (2026)

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
por: Zhang, Fuyao, et al.
Publicado: (2025)

Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning
por: Jiang, Yu, et al.
Publicado: (2025)

Information-theoretic Estimation of the Risk of Privacy Leaks
por: Odoh, Kenneth
Publicado: (2025)

BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel
por: Li, Hao, et al.
Publicado: (2025)

You Can't Trust Your Tag Neither: Privacy Leaks and Potential Legal Violations within the Google Tag Manager
por: Mertens, Gilles, et al.
Publicado: (2023)

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
por: Li, Zhangheng, et al.
Publicado: (2024)

Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks
por: Tsiolakis, Theodoros, et al.
Publicado: (2025)

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
por: Meier, Dominik, et al.
Publicado: (2025)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
por: Li, Na, et al.
Publicado: (2025)

Utilizing Large LanguageModels to Detect Privacy Leaks in Mini-App Code
por: Jiang, Liming
Publicado: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
por: Wu, Xiaoyu, et al.
Publicado: (2025)

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content
por: Chandna, Bhavik, et al.
Publicado: (2025)

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
por: Liu, Zhenlong, et al.
Publicado: (2024)

Label Inference Attacks against Federated Unlearning
por: Wang, Wei, et al.
Publicado: (2025)

Bayes-Nash Generative Privacy Against Membership Inference Attacks
por: Zhang, Tao, et al.
Publicado: (2024)

Membership Reference Attack against Laplace Mechanism of Differential Privacy
por: Huang, Wen
Publicado: (2024)

VidLeaks: Membership Inference Attacks Against Text-to-Video Models
por: Wang, Li, et al.
Publicado: (2026)

LeakGuard: Detecting Memory Leaks Accurately and Scalably
por: Liang, Hongliang, et al.
Publicado: (2025)

Membership Inference Attacks for Unseen Classes
por: Thaker, Pratiksha, et al.
Publicado: (2025)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
por: Ran, Delong, et al.
Publicado: (2025)

Privacy-Preserving Federated Unlearning with Certified Client Removal
por: Liu, Ziyao, et al.
Publicado: (2024)

Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning
por: Brimhall, Brennon, et al.
Publicado: (2025)

Efficient Unlearning with Privacy Guarantees
por: Domingo-Ferrer, Josep, et al.
Publicado: (2025)

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
por: Li, Xiangman, et al.
Publicado: (2025)

Guaranteeing Data Privacy in Federated Unlearning with Dynamic User Participation
por: Liu, Ziyao, et al.
Publicado: (2024)

Enter, Exit, Page Fault, Leak: Testing Isolation Boundaries for Microarchitectural Leaks
por: Oleksenko, Oleksii, et al.
Publicado: (2025)

The Sample Complexity of Membership Inference and Privacy Auditing
por: Haghifam, Mahdi, et al.
Publicado: (2025)

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

Membership Inference Attacks Against Vision-Language Models
por: Hu, Yuke, et al.
Publicado: (2025)

Enhancing Noisy Functional Encryption for Privacy-Preserving Machine Learning
por: Scheu-Hachtel, Linda, et al.
Publicado: (2025)

Private Links, Public Leaks: Consequences of Frictionless User Experience on the Security and Privacy Posture of SMS-Delivered URLs
por: Danish, Muhammad, et al.
Publicado: (2026)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
por: Wang, Weiqi, et al.
Publicado: (2025)

A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks
por: Liu, Hengzhu, et al.
Publicado: (2024)

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
por: Liu, Terrance, et al.
Publicado: (2025)