Copertina

Unveiling Privacy, Memorization, and Input Curvature Links

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ravikumar, Deepak, Soufleri, Efstathia, Hashemi, Abolfazl, Roy, Kaushik
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
di: Ravikumar, Deepak, et al.
Pubblicazione: (2024)

Finding the Muses: Identifying Coresets through Loss Trajectories
di: Nagaraj, Manish, et al.
Pubblicazione: (2025)

Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation
di: Soufleri, Efstathia, et al.
Pubblicazione: (2024)

Learning to Localize Leakage of Cryptographic Sensitive Variables
di: Gammell, Jimmy, et al.
Pubblicazione: (2025)

Position: Privacy Is Not Just Memorization!
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2025)

Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
di: Yin, Yi, et al.
Pubblicazione: (2025)

Extracting Memorized Training Data via Decomposition
di: Su, Ellen, et al.
Pubblicazione: (2024)

Have it your way: Individualized Privacy Assignment for DP-SGD
di: Boenisch, Franziska, et al.
Pubblicazione: (2023)

Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning
di: Ahamed, Sayyed Farid, et al.
Pubblicazione: (2024)

Robust Privacy: Inference-Time Privacy through Certified Robustness
di: Jin, Jiankai, et al.
Pubblicazione: (2026)

Beyond Data Privacy: New Privacy Risks for Large Language Models
di: Du, Yuntao, et al.
Pubblicazione: (2025)

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy
di: Kaiser, Johannes, et al.
Pubblicazione: (2026)

RAG with Differential Privacy
di: Grislain, Nicolas
Pubblicazione: (2024)

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
di: Ganev, Georgi, et al.
Pubblicazione: (2023)

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
di: Li, Jianwei, et al.
Pubblicazione: (2023)

DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning
di: Zhao, Kaixiang, et al.
Pubblicazione: (2025)

Privacy-Preserving Dynamic Assortment Selection
di: Cho, Young Hyun, et al.
Pubblicazione: (2024)

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

Privacy Auditing of Large Language Models
di: Panda, Ashwinee, et al.
Pubblicazione: (2025)

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
di: Tian, Huan, et al.
Pubblicazione: (2023)

Multiple-Input Auto-Encoder Guided Feature Selection for IoT Intrusion Detection Systems
di: Dinh, Phai Vu, et al.
Pubblicazione: (2024)

Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain
di: Raptis, Spyridon, et al.
Pubblicazione: (2025)

Provable Privacy with Non-Private Pre-Processing
di: Hu, Yaxi, et al.
Pubblicazione: (2024)

Bridging Privacy and Robustness for Trustworthy Machine Learning
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

Tight Auditing of Differential Privacy in MST and AIM
di: Ganev, Georgi, et al.
Pubblicazione: (2026)

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
di: Zhang, Guangsheng, et al.
Pubblicazione: (2022)

LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN
di: Zhang, Yuxing, et al.
Pubblicazione: (2024)

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
di: Sarwar, Nobin, et al.
Pubblicazione: (2025)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
di: Wang, Zhepeng, et al.
Pubblicazione: (2024)

Privacy-Preserving in Blockchain-based Federated Learning Systems
di: M., Sameera K., et al.
Pubblicazione: (2024)

SoK: Security and Privacy Risks of Healthcare AI
di: Chang, Yuanhaur, et al.
Pubblicazione: (2024)

Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
di: Bai, Shaojie, et al.
Pubblicazione: (2024)

Decentralized Federated Learning: A Survey on Security and Privacy
di: Hallaji, Ehsan, et al.
Pubblicazione: (2024)

Differential Privacy Mechanisms in Neural Tangent Kernel Regression
di: Gu, Jiuxiang, et al.
Pubblicazione: (2024)

Privacy Implications of Explainable AI in Data-Driven Systems
di: Ezzeddine, Fatima
Pubblicazione: (2024)

RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting
di: Shi, Zhan, et al.
Pubblicazione: (2025)

Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
di: Liu, Huikang, et al.
Pubblicazione: (2026)

Decoupling Generalizability and Membership Privacy Risks in Neural Networks
di: Fang, Xingli, et al.
Pubblicazione: (2026)

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
di: Yao, Zexi, et al.
Pubblicazione: (2025)

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks
di: Scheliga, Daniel, et al.
Pubblicazione: (2023)