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/AIPAG/SeqMIA

공식 코드

SeqMIA: Sequential-Metric Based Membership Inference Attack

https://github.com/AIRI-Institute/GLiRA

공식 코드

GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation

https://github.com/AhmedSalem2/ML-Leaks

공식 코드

ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

https://github.com/BehroozRazeghi/CLUB

공식 코드

Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility

https://github.com/BehroozRazeghi/Variational-Leakage

공식 코드

Variational Leakage: The Role of Information Complexity in Privacy Leakage

https://github.com/Brophy-E/ECG_GAN_MBD

공식 코드

Synthesis of Realistic ECG using Generative Adversarial Networks

https://github.com/DependableSystemsLab/code_poison_MIA

공식 코드

A Method to Facilitate Membership Inference Attacks in Deep Learning Models

https://github.com/DingfanChen/GAN-Leaks

공식 코드

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

https://github.com/EmilyAlsentzer/clinicalBERT

공식 코드

Publicly Available Clinical BERT Embeddings

https://github.com/Forsad/Stable-Polynomial-Train

공식 코드

A Training Framework for Optimal and Stable Training of Polynomial Neural Networks

https://github.com/HongshengHu/membership-inference-machine-learning-literature

공식 코드

Membership Inference Attacks on Machine Learning: A Survey

https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Healthcare/1.4.Biomedical_NER_SparkNLP_paper_reproduce.ipynb

공식 코드

Biomedical Named Entity Recognition at Scale

https://github.com/LaRiffle/AriaNN

공식 코드

ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

https://github.com/MLforHealth/MIMIC_Generalisation

공식 코드

Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks

https://github.com/MinChen00/UnlearningLeaks

공식 코드

When Machine Unlearning Jeopardizes Privacy

https://github.com/Raman1121/diffusion_memorization

공식 코드

The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation

https://github.com/SAP-samples/security-research-dp-hierarchical-text

공식 코드

On the privacy-utility trade-off in differentially private hierarchical text classification

https://github.com/SAP-samples/security-research-membership-inference-against-generative-networks

공식 코드

Reconstruction and Membership Inference Attacks against Generative Models

https://github.com/SAP-samples/security-research-membership-inference-and-differential-privacy

공식 코드

Assessing differentially private deep learning with Membership Inference

https://github.com/SamySam0/SynDeidMLM

공식 코드

Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling

https://github.com/Shawn-Shan/fawkes

공식 코드

Fawkes: Protecting Privacy against Unauthorized Deep Learning Models

https://github.com/TUM-AIMED/2.5DAttention

공식 코드

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging

https://github.com/VITA-Group/PA-HMDB51

공식 코드

Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset

https://github.com/a43992899/deid-vc

공식 코드

DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion

https://github.com/aabarr/Synthetic-Neurosurgical-Data

공식 코드

Zero-shot generation of synthetic neurosurgical data with large language models

https://github.com/aidotse/leakpro

공식 코드

Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning

https://github.com/andron00e/jast

공식 코드

Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning

https://github.com/angelpaulml17/DeIDClinic

공식 코드

DeIDClinic: A Multi-Layered Framework for De-identification of Clinical Free-text Data

https://github.com/anirbanmukherjeexd/rid-twin

공식 코드

RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos

https://github.com/anonjd/privacyai

공식 코드

Enhancing the De-identification of Personally Identifiable Information in Educational Data

https://github.com/appfl/cpbert

공식 코드

Enhancing Clinical Models with Pseudo Data for De-identification

https://github.com/ar-roy/dct-cryptonets

공식 코드

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

https://github.com/ayu987/deep-regression-unlearning

공식 코드

Deep Regression Unlearning

https://github.com/betterzhou/PHICON

공식 코드

PHICON: Improving Generalization of Clinical Text De-identification Models via Data Augmentation

https://github.com/bionlplab/radtext

공식 코드

Radiology Text Analysis System (RadText): Architecture and Evaluation

https://github.com/boschresearch/joint_anonymization_extraction

공식 코드

Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.