https://github.com/jiiahaoxu/masa
공식 코드Identify Backdoored Model in Federated Learning via Individual Unlearning
Papers with Code 아카이브
Machine Unlearning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/jimmy-di/camouflage-poisoning
공식 코드Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
https://github.com/jingruihou/numur
공식 코드https://github.com/jingwu321/scissorhands
공식 코드Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
https://github.com/jinzhuoran/rwku
공식 코드RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
https://github.com/jjbrophy47/dare_rf
공식 코드https://github.com/jjbrophy47/dart
공식 코드https://github.com/jpmorganchase/i2i-generator-unlearning
공식 코드https://github.com/jpmorganchase/l2l-generator-unlearning
공식 코드https://github.com/jwf40/information-theoretic-unlearning
공식 코드https://github.com/jwf40/zeroshot-unlearning-at-scale
공식 코드https://github.com/k1rezaei/restor
공식 코드https://github.com/kairanzhao/rum
공식 코드https://github.com/karuna-bhaila/llm_unlearning
공식 코드https://github.com/khu-agi/guide
공식 코드https://github.com/koudounasalkis/UnSLU-BENCH
공식 코드"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
https://github.com/krad-zz/Certified-Machine-Unlearning
공식 코드https://github.com/leitro/machineunlearning-docclassification
공식 코드https://github.com/lingzhi-wang/kgaunlearn
공식 코드KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
https://github.com/lioutang/unlearn-apollo-attack
공식 코드Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
https://github.com/lmeraser/lmeraser
공식 코드LMEraser: Large Model Unlearning through Adaptive Prompt Tuning
https://github.com/lucasbeerens/record
공식 코드https://github.com/martinpawel/openunlearn
공식 코드https://github.com/maybelizzy/ugbench
공식 코드Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
https://github.com/meghdad92/scrub
공식 코드https://github.com/mehrdadsaberi/msa_unlearning
공식 코드https://github.com/michele17284/awesome-privacy-preserving-llms
공식 코드Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
https://github.com/molereddy/Alternate-Preference-Optimization
공식 코드Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
https://github.com/momalab/ReVeil
공식 코드ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
https://github.com/msakarvadia/memorization
공식 코드https://github.com/nanboy-ronan/2f2l-federated-unlearning
공식 코드Forgettable Federated Linear Learning with Certified Data Unlearning
https://github.com/naver-ai/negmerge
공식 코드NegMerge: Consensual Weight Negation for Strong Machine Unlearning
https://github.com/ndb796/machineunlearning
공식 코드https://github.com/ngmarchant/attack-unlearning
공식 코드Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
https://github.com/nickypro/selective-pruning
공식 코드Dissecting Language Models: Machine Unlearning via Selective Pruning
https://github.com/ocram17/duck
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.