Buchumschlag

DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hmida, Firas Ben, Sbeih, Zain, Hailemariam, Philemon, Eshete, Birhanu
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Cryptography and Security Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples
von: Hmida, Firas Ben, et al.
Veröffentlicht: (2026)

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
von: Hmida, Firas Ben, et al.
Veröffentlicht: (2025)

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
von: Sui, Zhihao, et al.
Veröffentlicht: (2025)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
von: Nie, Yuzhou, et al.
Veröffentlicht: (2024)

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks
von: Panebianco, Francesco, et al.
Veröffentlicht: (2025)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
von: Wen, Yuxin, et al.
Veröffentlicht: (2024)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
von: Huang, Catherine, et al.
Veröffentlicht: (2024)

Pro-ZD: A Transferable Graph Neural Network Approach for Proactive Zero-Day Threats Mitigation
von: Basta, Nardine, et al.
Veröffentlicht: (2026)

Analysis of Privacy Leakage in Federated Large Language Models
von: Vu, Minh N., et al.
Veröffentlicht: (2024)

Ensembling Membership Inference Attacks Against Tabular Generative Models
von: Ward, Joshua, et al.
Veröffentlicht: (2025)

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

MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
von: Li, Jiacheng, et al.
Veröffentlicht: (2023)

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

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

Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge
von: Bertoli, Gustavo de Carvalho
Veröffentlicht: (2026)

From Data Leak to Secret Misses: The Impact of Data Leakage on Secret Detection Models
von: Soltaniani, Farnaz, et al.
Veröffentlicht: (2026)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
von: Meng, Jiayang, et al.
Veröffentlicht: (2025)

Rethinking Membership Inference Attacks Against Transfer Learning
von: Wu, Cong, et al.
Veröffentlicht: (2025)

Secure Aggregation is Not Private Against Membership Inference Attacks
von: Ngo, Khac-Hoang, et al.
Veröffentlicht: (2024)

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
von: Zhang, Boyang, et al.
Veröffentlicht: (2025)

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
von: Cretu, Ana-Maria, et al.
Veröffentlicht: (2023)

Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
von: Pradhan, Gauri, et al.
Veröffentlicht: (2025)

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

Membership Inference Attacks and Privacy in Topic Modeling
von: Manzonelli, Nico, et al.
Veröffentlicht: (2024)

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"
von: Schneider, Thomas, et al.
Veröffentlicht: (2024)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
von: Rashid, Md Rafi Ur, et al.
Veröffentlicht: (2023)

FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
von: Mahyar, Abtin, et al.
Veröffentlicht: (2026)

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

MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models
von: Shi, Shanghao, et al.
Veröffentlicht: (2024)

A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
von: Jebreel, Najeeb, et al.
Veröffentlicht: (2026)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
von: Zhang, Chenxiang, et al.
Veröffentlicht: (2025)

Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
von: Lumbut, Chayadon, et al.
Veröffentlicht: (2024)

A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
von: Shao, Jiawei, et al.
Veröffentlicht: (2023)

Improved Membership Inference Attacks Against Language Classification Models
von: Shachor, Shlomit, et al.
Veröffentlicht: (2023)

Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
von: Krčo, Nataša, et al.
Veröffentlicht: (2024)

Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation
von: Shi, Haonan, et al.
Veröffentlicht: (2025)

Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis
von: Ward, Joshua, et al.
Veröffentlicht: (2025)

Privacy Leakage via Output Label Space and Differentially Private Continual Learning
von: Tobaben, Marlon, et al.
Veröffentlicht: (2024)

Evaluating Privacy Leakage in Split Learning
von: Qiu, Xinchi, et al.
Veröffentlicht: (2023)

WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles
von: Mesana, Patrick, et al.
Veröffentlicht: (2024)