Papers with Code 아카이브
Machine Unlearning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Model State Arithmetic for Machine Unlearning
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
Orthogonal Soft Pruning for Efficient Class Unlearning
Verifiable Unlearning on Edge
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
Sharpness-Aware Machine Unlearning
Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
UCD: Unlearning in LLMs via Contrastive Decoding
Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
SoK: Machine Unlearning for Large Language Models
Certified Unlearning for Neural Networks
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Quantifying Cross-Modality Memorization in Vision-Language Models
Rethinking Machine Unlearning in Image Generation Models
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
SALAD: Systematic Assessment of Machine Unlearing on LLM-Aided Hardware Design
Towards Machine Unlearning for Paralinguistic Speech Processing
Speech Unlearning
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs
Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images
Soft Weighted Machine Unlearning
Leveraging Per-Instance Privacy for Machine Unlearning
Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
DUSK: Do Not Unlearn Shared Knowledge
UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
SEPS: A Separability Measure for Robust Unlearning in LLMs
Few-Shot Concept Unlearning with Low Rank Adaptation
Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.