Copertina

Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ke, Shuqi, Hou, Charlie, Oh, Sewoong, Fanti, Giulia
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DPZero: Private Fine-Tuning of Language Models without Backpropagation
di: Zhang, Liang, et al.
Pubblicazione: (2023)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
di: Zhang, Zhixin, et al.
Pubblicazione: (2025)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
di: Choquette-Choo, Christopher A., et al.
Pubblicazione: (2023)

On the Duality Between Sharpness-Aware Minimization and Adversarial Training
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Optimal Differentially Private Model Training with Public Data
di: Lowy, Andrew, et al.
Pubblicazione: (2023)

POPri: Private Federated Learning using Preference-Optimized Synthetic Data
di: Hou, Charlie, et al.
Pubblicazione: (2025)

A Queueing-Theoretic Framework for Dynamic Attack Surfaces: Data-Integrated Risk Analysis and Adaptive Defense
di: Yun, Jihyeon, et al.
Pubblicazione: (2026)

Secure LLM Fine-Tuning via Safety-Aware Probing
di: Wu, Chengcan, et al.
Pubblicazione: (2025)

Approximate and Weighted Data Reconstruction Attack in Federated Learning
di: Song, Yongcun, et al.
Pubblicazione: (2023)

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
di: Zhou, Duo, et al.
Pubblicazione: (2025)

On the Gradient Complexity of Private Optimization with Private Oracles
di: Menart, Michael, et al.
Pubblicazione: (2025)

Differentially Private Bilevel Optimization
di: Kornowski, Guy
Pubblicazione: (2024)

How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
di: Lowy, Andrew, et al.
Pubblicazione: (2024)

On Model Protection in Federated Learning against Eavesdropping Attacks
di: Maity, Dipankar, et al.
Pubblicazione: (2025)

Differentially Private Random Block Coordinate Descent
di: Maranjyan, Artavazd, et al.
Pubblicazione: (2024)

Private Zeroth-Order Nonsmooth Nonconvex Optimization
di: Zhang, Qinzi, et al.
Pubblicazione: (2024)

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
di: Kornowski, Guy, et al.
Pubblicazione: (2024)

Distributed Online Private Learning of Convex Nondecomposable Objectives
di: Cheng, Huqiang, et al.
Pubblicazione: (2022)

Public-data Assisted Private Stochastic Optimization: Power and Limitations
di: Ullah, Enayat, et al.
Pubblicazione: (2024)

Faster Algorithms for User-Level Private Stochastic Convex Optimization
di: Lowy, Andrew, et al.
Pubblicazione: (2024)

The Power of Sampling: Dimension-free Risk Bounds in Private ERM
di: Lee, Yin Tat, et al.
Pubblicazione: (2021)

The Relative Gaussian Mechanism and its Application to Private Gradient Descent
di: Hendrikx, Hadrien, et al.
Pubblicazione: (2023)

Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter
di: Lowy, Andrew, et al.
Pubblicazione: (2022)

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
di: Hou, Charlie, et al.
Pubblicazione: (2024)

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
di: Islamov, Rustem, et al.
Pubblicazione: (2026)

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
di: Lowy, Andrew, et al.
Pubblicazione: (2025)

Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
di: Bassily, Raef, et al.
Pubblicazione: (2024)

Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates
di: Menart, Michael, et al.
Pubblicazione: (2023)

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
di: Lowy, Andrew, et al.
Pubblicazione: (2021)

Differentially Private High Dimensional Bandits
di: Shukla, Apurv
Pubblicazione: (2024)

Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
di: González, Tomás, et al.
Pubblicazione: (2024)

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
di: Gao, Changyu, et al.
Pubblicazione: (2024)

Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?
di: Du, Hao, et al.
Pubblicazione: (2025)

Boosting Jailbreak Attack with Momentum
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Exploring the Robustness of In-Context Learning with Noisy Labels
di: Cheng, Chen, et al.
Pubblicazione: (2024)

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
di: Zhang, Yihao, et al.
Pubblicazione: (2024)

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
di: Wu, Chengcan, et al.
Pubblicazione: (2025)

RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
di: Wei, Zeming, et al.
Pubblicazione: (2026)

Identifying and Understanding Cross-Class Features in Adversarial Training
di: Wei, Zeming, et al.
Pubblicazione: (2025)

Efficient Optimization Algorithms for Linear Adversarial Training
di: RIbeiro, Antônio H., et al.
Pubblicazione: (2024)