Copertina

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tran, Hoang, Ramirez, Jorge, Wang, Jiayi, Bocchinfuso, Alberto, Stanley, Christopher, Laiu, M. Paul
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Publishing Wikipedia usage data with strong privacy guarantees
di: Adeleye, Temilola, et al.
Pubblicazione: (2023)

Obtaining $(ε,δ)$-differential privacy guarantees when using a Poisson mechanism to synthesize contingency tables
di: Jackson, James, et al.
Pubblicazione: (2024)

Advancing privacy in learning analytics using differential privacy
di: Liu, Qinyi, et al.
Pubblicazione: (2025)

Robust softmax aggregation on blockchain based federated learning with convergence guarantee
di: Wu, Huiyu, et al.
Pubblicazione: (2023)

Federated learning with differential privacy and an untrusted aggregator
di: Liu, Kunlong, et al.
Pubblicazione: (2023)

A privacy preserving querying mechanism with high utility for electric vehicles
di: Atmaca, Ugur Ilker, et al.
Pubblicazione: (2022)

Comparing privacy notions for protection against reconstruction attacks in machine learning
di: Biswas, Sayan, et al.
Pubblicazione: (2025)

Differential privacy for symmetric log-concave mechanisms
di: Vinterbo, Staal A.
Pubblicazione: (2022)

Predicting memorization within Large Language Models fine-tuned for classification
di: Dentan, Jérémie, et al.
Pubblicazione: (2024)

Modeling interdependent privacy threats
di: Liu, Shuaishuai, et al.
Pubblicazione: (2025)

LLMs on support of privacy and security of mobile apps: state of the art and research directions
di: Nguyen, Tran Thanh Lam, et al.
Pubblicazione: (2025)

H-LPS: a hybrid approach for user's location privacy in location-based services
di: Sabir, Sonia, et al.
Pubblicazione: (2022)

Optimal partition selection with Rényi differential privacy
di: Harrison, Charlie, et al.
Pubblicazione: (2026)

RIOT-based smart metering system for privacy-preserving data aggregation using watermarking and encryption
di: Kabir, Farzana, et al.
Pubblicazione: (2025)

Sketches-based join size estimation under local differential privacy
di: Zhang, Meifan, et al.
Pubblicazione: (2024)

Emission Impossible: privacy-preserving carbon emissions claims
di: Man, Jessica, et al.
Pubblicazione: (2025)

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
di: Jha, Piyush, et al.
Pubblicazione: (2024)

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
di: Huang, Tiansheng, et al.
Pubblicazione: (2024)

FedDCL: a federated data collaboration learning as a hybrid-type privacy-preserving framework based on federated learning and data collaboration
di: Imakura, Akira, et al.
Pubblicazione: (2024)

Tangent differential privacy
di: Ying, Lexing
Pubblicazione: (2024)

Collection, usage and privacy of mobility data in the enterprise and public administrations
di: Kapp, Alexandra
Pubblicazione: (2024)

Accountable authentication with privacy protection: The Larch system for universal login
di: Dauterman, Emma, et al.
Pubblicazione: (2023)

Optimizing seed inputs in fuzzing with machine learning
di: Cheng, Liang, et al.
Pubblicazione: (2019)

zkDFL: An efficient and privacy-preserving decentralized federated learning with zero-knowledge proof
di: Ahmadi, Mojtaba, et al.
Pubblicazione: (2023)

Correlation inference attacks against machine learning models
di: Creţu, Ana-Maria, et al.
Pubblicazione: (2021)

MultiBallot: Verifiable and privacy-preserving E-Collecting in the Swiss setting
di: Moser, Florian, et al.
Pubblicazione: (2026)

Lockcoin: a secure and privacy-preserving mix service for bitcoin anonymity
di: Bao, Zijian, et al.
Pubblicazione: (2018)

Can large language models be privacy preserving and fair medical coders?
di: Dadsetan, Ali, et al.
Pubblicazione: (2024)

Integrating uncertainty quantification into randomized smoothing based robustness guarantees
di: Däubener, Sina, et al.
Pubblicazione: (2024)

Showcasing standards and approaches for cybersecurity, safety, and privacy issues in connected and autonomous vehicles
di: Czekster, Ricardo M.
Pubblicazione: (2025)

Semi-Supervised Learning for Anomaly Detection in Blockchain-based Supply Chains
di: Son, Do Hai, et al.
Pubblicazione: (2024)

Requiem for a drone: a machine-learning based framework for stealthy attacks against unmanned autonomous vehicles
di: Kim, Kyo Hyun, et al.
Pubblicazione: (2024)

Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
di: Abdennebi, Anes, et al.
Pubblicazione: (2026)

Rényi divergence-based uniformity guarantees for $k$-universal hash functions
di: Pathegama, Madhura, et al.
Pubblicazione: (2024)

Fine-tuning Large Language Models for DGA and DNS Exfiltration Detection
di: Sayed, Md Abu, et al.
Pubblicazione: (2024)

Flexible and scalable privacy assessment for very large datasets, with an application to official governmental microdata
di: Alvim, Mário S., et al.
Pubblicazione: (2022)

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
di: Zeng, Yi, et al.
Pubblicazione: (2024)

On the differential privacy of dynamic location obfuscation with personalized error bounds
di: Shun, Zhang, et al.
Pubblicazione: (2021)

A novel analysis of utility in privacy pipelines, using Kronecker products and quantitative information flow
di: Alvim, Mário S., et al.
Pubblicazione: (2023)

Publicly auditable privacy-preserving electoral rolls
di: Agrawal, Prashant, et al.
Pubblicazione: (2024)