← Back to all news
arXiv Machine Learning 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.

Related stories

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
llmssafety
More like this →
arXiv AI
Sep 24

When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense

The paper introduces Fed-ADR, a coordinated attack framework where a malicious orchestrator server directs heterogeneous adversarial clients to adapt their gradient updates in real time, thereby evading existing federated learning defenses and drastically reducing global model accuracy. It also presents a lightweight detection mechanism that estimates true client gradients from historical data to spot coordinated attacks, and an in-situ recovery method that restores model performance without restarting training. Experiments on MNIST, Fashion‑MNIST, and CIFAR‑10 show the attack can drop accuracy from over 90% to below 10%, while the defense can recover accuracy to above 90% within a few rounds at a computational cost at least 20× lower than retraining from scratch.

By Mohamed Shaaban, Ahmed Abdelnaby, Mohamed Elmahallawy
roboticsbenchmarkssafety
More like this →