paper-with-me

홈 › Papers

Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks

2024-01-11 · Jing Wu, Mehrtash Harandi

Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we present a new machine unlearning approach Scissorhands. Initially, Scissorhands identifies the most pertinent parameters in the given model relative to the forgetting data via connection sensitivity. By reinitializing the most influential top-k percent of these parameters, a trimmed model for erasing the influence of the forgetting data is obtained. Subsequently, Scissorhands fine-tunes the trimmed model with a gradient projection-based approach, seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data. Our experimental results, conducted across image classification and image generation tasks, demonstrate that Scissorhands, showcases competitive performance when compared to existing methods. Source code is available at https://github.com/JingWu321/Scissorhands.

📄 PDF Abstract BibTeX arXiv:2401.06187

Code (1)

jingwu321/scissorhands 공식 구현 pytorch

Tasks

image-classificationImage ClassificationImage GenerationMachine UnlearningSensitivity

Similar Papers 제목 키워드 기반

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

2023-05-26 · NeurIPS 2023 11

Large language models(LLMs) have sparked a new wave of exciting AI applications. Hosting these models at scale requires significant memory resources. One crucial memory bottleneck for the deployment stems from the contex…

Quantization

Fault-Tolerant Control Design in Scrubber Plant with Fault on Sensor Sensitivity

2023-04-09 · Moh Kamalul Wafi, Katherin Indriawati

The concept of fault-tolerant control has extensively been explored with various mapping of development. It starts from the system characteristic, the robustness of the controller, estimation methods and optimization, to…

Sensitivity

Enterprise Disk Drive Scrubbing Based on Mondrian Conformal Predictors

2023-06-01 · Rahul Vishwakarma, Jinha Hwang, Soundouss Messoudi, Ava Hedayatipour

Disk scrubbing is a process aimed at resolving read errors on disks by reading data from the disk. However, scrubbing the entire storage array at once can adversely impact system performance, particularly during periods …

Conformal Prediction

Analyzing Leakage of Personally Identifiable Information in Language Models

2023-02-01 · Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople 외

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Informat…

Sentence

ContractScrub: A benchmark for final review of legal contracts

2026-08-20 · Yejin Bang, Kirsty Fielding, Brandan Oliver, Brian Birke 외 arxiv

Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,'' the final review of transactional agreements for er…