Papers with Code 아카이브
Model extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
Model extraction attacks, aka model stealing attacks, are used to extract the parameters from the target model. Ideally, the adversary will be able to steal and replicate a model that will have a very similar performance to the target model.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/patriziobellan86/processextractionfromtextsotaandchallenges
공식 코드https://github.com/qianc62/MGTC
공식 코드An Approach for Process Model Extraction By Multi-Grained Text Classification
https://github.com/rinnesz/gro-gradient-based-ranking-optimization
공식 코드Defense Against Model Extraction Attacks on Recommender Systems
https://github.com/ssg-research/dawn-dynamic-adversarial-watermarking-of-neural-networks
공식 코드https://github.com/stratosphereips/meme_malware_rl
공식 코드The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
https://github.com/stratosphereips/model_extraction_malware
공식 코드Stealing and Evading Malware Classifiers and Antivirus at Low False Positive Conditions
https://github.com/vardetect/vardetect
공식 코드https://github.com/vidalt/Tree-Extractor
공식 코드From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
https://github.com/vidmodex/vidmodex
공식 코드VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
https://github.com/weizeming/extract_wfa_from_rnn_for_nl
공식 코드Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks
https://github.com/xingjunm/awesome-large-model-safety
공식 코드Safety at Scale: A Comprehensive Survey of Large Model Safety
https://github.com/xlhex/extract_and_transfer
공식 코드Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
https://github.com/xlhex/nlg_api_watermark
공식 코드Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
https://github.com/xuandongzhao/ginseq
공식 코드Protecting Language Generation Models via Invisible Watermarking
https://github.com/xuandongzhao/ginsew
공식 코드Protecting Language Generation Models via Invisible Watermarking
https://github.com/xythink/same
공식 코드SAME: Sample Reconstruction against Model Extraction Attacks
https://github.com/yjw1029/embmarker
공식 코드https://github.com/yueeeeeeee/recsys-extraction-attack
공식 코드Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
https://github.com/zk4-ps/eaas-embedding-watermark
공식 코드https://github.com/MindSpore-scientific/code-12/tree/main/CME
https://github.com/ayberkuckun/dnn-fingerprinting
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
https://github.com/bcoqueret/Side_channel_cryptanalytic_extraction_of_DNN
https://github.com/cleverhans-lab/model-extraction-iclr
https://github.com/k1l1/SLT
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
https://github.com/rorschachchen/entangled-watermark-torch
https://github.com/ssg-research/conflicts-in-ml-protection-mechanisms
On the Effectiveness of Dataset Watermarking in Adversarial Settings
https://github.com/ssg-research/falseclaims
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.