arXiv Machine Learning September 14, 2026 By Ayushi Thakur, Ruchir Gupta, Amit Kumar Jaiswal, Prayag Tiwari

Correlation-Guided Fast Machine Unlearning via Hessian Analysis

Read the original on arXiv Machine Learning →

The paper presents a fast machine unlearning method that uses Hessian analysis to identify correlated training data and applies a closed‑form update rule. This approach achieves an 82× speedup over traditional influence‑function unlearning while maintaining or slightly improving model accuracy. Experiments on seven dataset‑architecture pairs, including CIFAR‑100 with ResNet‑50, show strong forgetting performance and low vulnerability to membership inference attacks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 10

SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

The paper introduces Dynamic DAE Guardrails (DSG), a method that uses Dynamic Sparse Autoencoders to perform precision unlearning in large language models. DSG leverages principled feature selection and a dynamic classifier to target activation-based unlearning, outperforming existing gradient‑based methods in terms of computational efficiency, stability, sequential unlearning, resistance to relearning attacks, data efficiency, and interpretability.

By Aashiq Muhamed, Jacopo Bonato, Mona Diab, Virginia Smith

llms safety

arXiv AI

Jun 9

Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

arXiv:2605. 20341v2 Announce Type: replace-cross Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive.

By Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi, Omid Kashefi

llms safety

arXiv AI

Aug 10

TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning

arXiv:2608. 07274v1 Announce Type: cross Abstract: Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead.

By Yuhan Xie, Jingrong Huang, Chen Lyu

benchmarks safety

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

arXiv Machine Learning

Jun 16

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.

By Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou

llms fine-tuning safety

arXiv Machine Learning

Jun 8

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning

arXiv:2412. 09119v3 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment.

By Youssef Allouah, Joshua Kazdan, Rachid Guerraoui, Sanmi Koyejo

safety

One email a morning, machine-written

Related stories

SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning