Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 6 of 6 for “"Machine Unlearning"”.

  1. Layered Unlearning for Adversarial Relearning

    … methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes them easy to bypass through prompt engineering or relearning. Recent results suggest that …

    mit Repository record for Layered Unlearning for Adversarial Relearning (opens in a new tab)

  2. Approaches to Artistic Style Suppression: An Evaluation Framework for Copyright Compliance in Generative Artificial Intelligence

    … learned from training data. Parameter-based machine unlearning methods address these concerns by modifying model weights to reduce learned associations, but their computational requirements make them impractical in resource-constrained environments. This thesis investigates inference-time …

    stellenbosch Repository record for Approaches to Artistic Style Suppression: An Evaluation Framework for Copyright Compliance in Generative Artificial Intelligence (opens in a new tab)

  3. Order-Leading Branch and Bound for Neural Network Verification

    … errors across continual retraining, pruning, or unlearning throughout the lifecycle. This thesis addresses that gap by reconceiving deep learning model verification as a scalable, life-cycle-aware service rather than a one-off, model-centric exercise. The thesis is reasoning and opening the black …

    unsw Repository record for Order-Leading Branch and Bound for Neural Network Verification (opens in a new tab)

  4. Investigating Model Editing for Unlearning in Large Language Models

    … that is captured in the knowledge of the model. Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for models with large numbers of parameters or fail to remove the entire scope of information without harming performance in the knowledge that is …

    mit Repository record for Investigating Model Editing for Unlearning in Large Language Models (opens in a new tab)

  5. Machine Learning through the Lens of Data

    Many critical challenges in machine learning—e.g., debugging model behavior or selecting good training data—require us to relate outputs of models back to the training data. The goal of predictive data attribution, the focus of this thesis, is to precisely characterize the resulting model behavior …

    mit Repository record for Machine Learning through the Lens of Data (opens in a new tab)

  6. Topics in efficient and privacy-preserving storage system design

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-12-01

    uiuc Repository record for Topics in efficient and privacy-preserving storage system design (opens in a new tab)