8 citations · 17 across the 16 of their papers we have counts for
12 papers · 1 filter
Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
Stefan Schoepf, Michael Curtis Mozer, Nicole Elyse Mitchell +4
Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address th…
MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
Stefan Schoepf, Muhammad Zaid Hameed, Ambrish Rawat +4
With LLM usage rapidly increasing, their vulnerability to jailbreaks that create harmful outputs are a major security risk. As new jailbreaking strategies emerge and models are cha…
Random Walk Guided Hyperbolic Graph Distillation
Yunbo Long, Liming Xu, Stefan Schoepf +1
Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to g…
Learning to Forget using Hypernetworks
Jose Miguel Lara Rangel, Stefan Schoepf, Jack Foster +2
Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations.…
ConDa: Fast Federated Unlearning with Contribution Dampening
Vikram S Chundawat, Pushkar Niroula, Prasanna Dhungana +3
Federated learning (FL) has enabled collaborative model training across decentralized data sources or clients. While adding new participants to a shared model does not pose great t…
Potion: Towards Poison Unlearning
Stefan Schoepf, Jack Foster, Alexandra Brintrup
Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving…
Loss-Free Machine Unlearning
Jack Foster, Stefan Schoepf, Alexandra Brintrup
We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information…
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
Stefan Schoepf, Jack Foster, Alexandra Brintrup
Data entry constitutes a fundamental component of the machine learning pipeline, yet it frequently results in the introduction of labelling errors. When a model has been trained on…
An Information Theoretic Approach to Machine Unlearning
Jack Foster, Kyle Fogarty, Stefan Schoepf +3
To comply with AI and data regulations, the need to forget private or copyrighted information from trained machine learning models is increasingly important. The key challenge in u…
Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
Jack Foster, Stefan Schoepf, Alexandra Brintrup
Machine unlearning, the ability for a machine learning model to forget, is becoming increasingly important to comply with data privacy regulations, as well as to remove harmful, ma…
Identifying contributors to supply chain outcomes in a multi-echelon setting: a decentralised approach
Stefan Schoepf, Jack Foster, Alexandra Brintrup
Organisations often struggle to identify the causes of change in metrics such as product quality and delivery duration. This task becomes increasingly challenging when the cause li…
Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem
Stefan Schoepf, Stephen Mak, Julian Senoner +3
Heavy goods vehicles are vital backbones of the supply chain delivery system but also contribute significantly to carbon emissions with only 60% loading efficiency in the United Ki…