https://github.com/bridgesra/expm_nf_mimic3_results_code
공식 코드Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?
Papers with Code 아카이브
De-identification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 0
- 보존된 평가 기록
- 0
De-identification is the task of detecting privacy-related entities in text, such as person names, emails and contact data.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/cardwizard/membershipInferenceLottery
공식 코드https://github.com/code-lukas/medical_image_deidentification
공식 코드De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy
https://github.com/computationalprivacy/mosaic_memory
공식 코드https://github.com/csong27/membership-inference
공식 코드Membership Inference Attacks against Machine Learning Models
https://github.com/drndr/bert_ent_attack
공식 코드https://github.com/duchenzhuang/flowencrypt
공식 코드https://github.com/dvl-tum/ciagan
공식 코드CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
https://github.com/ellisalicante/ma-fl-mia
공식 코드https://github.com/exploration-lab/llm-for-clinical-report-generation-deidentification
공식 코드Generation and De-Identification of Indian Clinical Discharge Summaries using LLMs
https://github.com/facebookresearch/Ego4d
공식 코드https://github.com/facebookresearch/label_dp_antipodes
공식 코드https://github.com/factral/privdl
공식 코드Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
https://github.com/friedronaldo/primitives-ps
공식 코드https://github.com/fseclab-osaka/mia-diffusion
공식 코드https://github.com/fzi-forschungszentrum-informatik/fadm
공식 코드Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models
https://github.com/g-pichler/dishonest_mia
공식 코드Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
https://github.com/giladcohen/sif_mi_attack
공식 코드https://github.com/google-research/arxiv-latex-cleaner
공식 코드Computational Job Market Analysis with Natural Language Processing
https://github.com/hassanalikhatim/amia
공식 코드Membership Inference Attacks on DNNs using Adversarial Perturbations
https://github.com/hcholab/k-salsa
공식 코드k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment
https://github.com/hreynaud/echonet-synthetic
공식 코드EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing
https://github.com/htwang14/PA-HMDB51
공식 코드Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
https://github.com/huang-research-group/LDPbandit2020
공식 코드Locally Differentially Private (Contextual) Bandits Learning
https://github.com/hugomcp/uu-net
공식 코드The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage
https://github.com/hukkelas/deep_privacy2
공식 코드https://github.com/hukkelas/full_body_anonymization
공식 코드https://github.com/hyhmia/BlindMI
공식 코드Practical Blind Membership Inference Attack via Differential Comparisons
https://github.com/iamgroot42/auditingmi
공식 코드Do Parameters Reveal More than Loss for Membership Inference?
https://github.com/iamgroot42/iha_hild
공식 코드Do Parameters Reveal More than Loss for Membership Inference?
https://github.com/iamgroot42/mimir
공식 코드Do Membership Inference Attacks Work on Large Language Models?
https://github.com/icescentral/MASK_public
공식 코드MASK: A flexible framework to facilitate de-identification of clinical texts
https://github.com/iyempissy/rebMIGraph
공식 코드https://github.com/izakariyya/idg-dp
공식 코드https://github.com/jayoungkim408/mia
공식 코드An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models
https://github.com/jiangnanh/ppml-workshop
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.