Copertina

Improving Unlearning with Model Updates Probably Aligned with Gradients

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dine, Virgile, Furon, Teddy, Faure, Charly
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning
di: Dine, Virgile, et al.
Pubblicazione: (2026)

WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
di: Giboulot, Eva, et al.
Pubblicazione: (2024)

Watermarking Makes Language Models Radioactive
di: Sander, Tom, et al.
Pubblicazione: (2024)

Task-Agnostic Attacks Against Vision Foundation Models
di: Pulfer, Brian, et al.
Pubblicazione: (2025)

Backdoor Attacks on Deep Learning Face Detection
di: Roux, Quentin Le, et al.
Pubblicazione: (2025)

Targeted Unlearning with Single Layer Unlearning Gradient
di: Cai, Zikui, et al.
Pubblicazione: (2024)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
di: Spohn, Philipp, et al.
Pubblicazione: (2025)

Label Smoothing Improves Gradient Ascent in LLM Unlearning
di: Pang, Zirui, et al.
Pubblicazione: (2025)

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
di: Roux, Quentin Le, et al.
Pubblicazione: (2025)

Pulling the Carpet Below the Learner's Feet: Genetic Algorithm To Learn Ensemble Machine Learning Model During Concept Drift
di: Lazebnik, Teddy
Pubblicazione: (2024)

Multi-Objective Reference-Aligned Machine Unlearning
di: Khosrowshahli, Rasa, et al.
Pubblicazione: (2026)

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery
di: Zhao, Wenwei, et al.
Pubblicazione: (2026)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
di: Chien, Eli, et al.
Pubblicazione: (2024)

Combining Normalizing Flows and Quasi-Monte Carlo
di: Andral, Charly
Pubblicazione: (2024)

Introducing 'Inside' Out of Distribution
di: Lazebnik, Teddy
Pubblicazione: (2024)

CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
di: Miao, Jiaxing, et al.
Pubblicazione: (2025)

Descend or Rewind? Stochastic Gradient Descent Unlearning
di: Mu, Siqiao, et al.
Pubblicazione: (2025)

Towards Aligned Data Forgetting via Twin Machine Unlearning
di: Niu, Zhenxing, et al.
Pubblicazione: (2025)

AdaProb: Efficient Machine Unlearning via Adaptive Probability
di: Zhao, Zihao, et al.
Pubblicazione: (2024)

Unlearning Backdoor Attacks through Gradient-Based Model Pruning
di: Dunnett, Kealan, et al.
Pubblicazione: (2024)

Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning
di: Nilsson, Ivo Osterberg, et al.
Pubblicazione: (2026)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
di: Huang, Tao, et al.
Pubblicazione: (2024)

Label Smoothing Improves Machine Unlearning
di: Di, Zonglin, et al.
Pubblicazione: (2024)

Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback
di: Chen, Xin, et al.
Pubblicazione: (2024)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
di: Huang, Zhuo, et al.
Pubblicazione: (2026)

Controllable Machine Unlearning via Gradient Pivoting
di: Hwang, Youngsik, et al.
Pubblicazione: (2025)

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment
di: Li, Shipeng, et al.
Pubblicazione: (2025)

Towards Aligned Data Removal via Twin Machine Unlearning
di: Ji, Haoxuan, et al.
Pubblicazione: (2024)

Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
di: Patel, Gaurav, et al.
Pubblicazione: (2025)

Gradient Transformer: Learning to Generate Updates for LLMs
di: Nguyen, Binh-Nguyen, et al.
Pubblicazione: (2026)

Lethe:Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning
di: Tan, Hanwei, et al.
Pubblicazione: (2026)

Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning
di: Grimes, Keltin, et al.
Pubblicazione: (2024)

Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing
di: Toral, Lukas, et al.
Pubblicazione: (2025)

Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization
di: Shamsian, Aviv, et al.
Pubblicazione: (2025)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
di: Wang, Qizhou, et al.
Pubblicazione: (2025)

Data Augmentation for Deep Learning Regression Tasks by Machine Learning Models
di: Shmuel, Assaf, et al.
Pubblicazione: (2025)

Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
di: Xu, Heng, et al.
Pubblicazione: (2024)

TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
di: Garg, Isha, et al.
Pubblicazione: (2022)

Improved Localized Machine Unlearning Through the Lens of Memorization
di: Torkzadehmahani, Reihaneh, et al.
Pubblicazione: (2024)

Stochastic Gradient Methods with Preconditioned Updates
di: Sadiev, Abdurakhmon, et al.
Pubblicazione: (2022)