awesome-machine-unlearning

awesome-machine-unlearning copied to clipboard

Scope: Model agnostic machine Unlearning , No retain dataset used (Zero-shot) Title: Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images link...

jbonato1

New paper about vulnerability of machine unlearning

1

https://arxiv.org/abs/2407.05112v1

tianzheng4

New paper on poison unlearning

1

Potion: Towards Poison Unlearning ArXiv: https://arxiv.org/abs/2406.09173 GitHub: https://github.com/if-loops/towards_poison_unlearning

if-loops

New paper about LLM Unlearning Benchmark(parametric-based)

1

The new paper about LLM Unlearning Benchmark (parametric-based) Arxiv: arxiv.org/abs/2406.11614 Website: https://yihuaihong.github.io/ConceptVectors.github.io/ Github: https://github.com/yihuaihong/ConceptVectors

yihuaihong

New paper(s) on machine unlearning

1

1. mismatched machine unlearning Title: Decoupling the Class Label and the Target Concept in Machine Unlearning arXiv: https://arxiv.org/abs/2406.08288 2. evaluation of LLM unlearning Title: Unlearning with Control: Assessing Real-world Utility...

ZFancy

New paper(s) about federated unlearning

1

Federated Unlearning: a Perspective of Stability and Fairness https://arxiv.org/abs/2402.01276

tamlhp

Multi-Modal Recommendation Unlearning https://arxiv.org/abs/2405.15328

tamlhp

New paper(s) on machine unlearning applications

1

Learning and Unlearning to Operate Profitable Secure Electric Vehicle Charging https://ieeexplore.ieee.org/abstract/document/10541863

tamlhp

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience https://arxiv.org/abs/2405.18040

tamlhp

New arXiv paper(s) about machine unlearning

2

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models https://arxiv.org/abs/2405.15234

tamlhp