Fetching the paper…
Reading the bibliography…
Today, creators of data-hungry deep neural networks (DNNs) scour the Internet for training fodder, leaving users with little control over or knowledge of when their data is appropriated for model training.
Discriminatory analysis - nonparametric discrimination: consistency properties
1951
Earlier work this paper cites.
Label-only membership inference attacks
1974
Earlier work this paper cites.
Discriminability-based transfer between neural networks
1992
Earlier work this paper cites.
ImageNet: A Large-Scale Hierarchical Image Database
2009
Earlier work this paper cites.
Attribute and simile classifiers for face verification
2009
Earlier work this paper cites.
Detection of Traffic Signs in Real-World Images: The German Traffic Sign Detection Benchmark
2013
Earlier work this paper cites.
A data-driven approach to cleaning large face datasets
2014
Earlier work this paper cites.
Learning face representation from scratch
2014
Earlier work this paper cites.
Facenet: A unified embedding for face recognition and clustering
2015
Earlier work this paper cites.
Deep learning with differential privacy
2016
Earlier work this paper cites.
A closer look at memorization in deep networks
2017
Earlier work this paper cites.
Documentation for Face++ API, 2017
2017
Earlier work this paper cites.
Badnets: Identifying vulnerabilities in the machine learning model supply chain
2017
Earlier work this paper cites.
Membership inference attacks against machine learning models
2017
Earlier work this paper cites.
Machine learning models that remember too much
2017
Earlier work this paper cites.
Detecting backdoor attacks on deep neural networks by activation clustering
2018
Earlier work this paper cites.
2018 reform of eu data protection rules
2018
Earlier work this paper cites.
Understanding membership inferences on well-generalized learning models
2018
Earlier work this paper cites.
Learning Differentially Private Recurrent Language Models
2018
Earlier work this paper cites.
Poison frogs! targeted clean-label poisoning attacks on neural networks
2018
Earlier work this paper cites.
A survey on deep transfer learning
2018
Earlier work this paper cites.
Spectral signatures in backdoor attacks
2018
Earlier work this paper cites.
Cosface: Large margin cosine loss for deep face recognition
2018
Earlier work this paper cites.
Privacy risk in machine learning: Analyzing the connection to overfitting
2018
Earlier work this paper cites.
The secret sharer: Evaluating and testing unintended memorization in neural networks
2019
Earlier work this paper cites.
Gmail smart compose: Real-time assisted writing
2019
Earlier work this paper cites.
Arcface: Additive angular margin loss for deep face recognition
2019
Earlier work this paper cites.
Certified data removal from machine learning models
2019
Cited alongside, same era.
Memguard: Defending against black-box membership inference attacks via adversarial examples
2019
Cited alongside, same era.
The audio auditor: user-level membership inference in Internet of Things voice services
2019
Cited alongside, same era.
Learning with bad training data via iterative trimmed loss minimization
2019
Cited alongside, same era.
Facial recognition’s ‘dirty little secret’: Millions of online photos scraped without consent
2019
Cited alongside, same era.
Auditing data provenance in text-generation models
MagFace: A Universal Representation for Face Recognition and Quality Assessment
2021
Later among the works it cites.
Salient imagenet: How to discover spurious features in deep learning?
2021
Later among the works it cites.
Backdoor attacks against deep learning systems in the physical world
2021
Later among the works it cites.
Opacus: User-friendly differential privacy library in PyTorch
2021
Later among the works it cites.
Understanding deep learning (still) requires rethinking generalization
2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
2019
Cited alongside, same era.
Language models are few-shot learners
2020
Cited alongside, same era.
Does learning require memorization? a short tale about a long tail
2020
Cited alongside, same era.
What neural networks memorize and why: Discovering the long tail via influence estimation
2020
Cited alongside, same era.
Witches’ brew: Industrial scale data poisoning via gradient matching
2020
Cited alongside, same era.
The Secretive Company that May End Privacy as We Know It
2020
Cited alongside, same era.
Membership inference attacks on sequence-to-sequence models: Is my data in your machine translation system?
2020
Cited alongside, same era.
2021
Later among the works it cites.
On the Effectiveness of Dataset Watermarking
2022
Closest in time.
Classifying Images with Vision and Core ML, 2022
2022
Closest in time.
Documentation for AWS Rekognition, 2022
2022
Closest in time.
Documentation for Azure Face API, 2022
2022
Closest in time.
Predict for image classification, 2022
2022
Closest in time.
What is Amazon Rekognition?, 2022
2022
Closest in time.
Membership Inference via Backdooring
2022
Closest in time.
This site tells you if photos of you were used to train the AI, 2022
2022
Closest in time.
Woman horrified to discover her private medical photos were being used to train ai, 2022
2022
Closest in time.
User-Level Membership Inference Attack against Metric Embedding Learning
2022
Closest in time.
Can backdoor attacks survive time-varying models?
2022
Closest in time.
Google faces fresh class action-style suit in UK over DeepMind NHS patient data scandal
2022
Closest in time.
Spuriosity rankings: Sorting data for spurious correlation robustness
2022
Closest in time.
Collaboration challenges in building ml-enabled systems: Communication, documentation, engineering, and process
2022
Closest in time.
Fight Poison with Poison: Detecting Backdoor Poison Samples via Decoupling Benign Correlations
2022
Closest in time.
Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
2022
Closest in time.
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
2022
Closest in time.
Understanding Rare Spurious Correlations in Neural Networks
2022
Closest in time.
Narcissus: A practical clean-label backdoor attack with limited information
2022
Closest in time.
OPT: Open pre-trained transformer language models
2022
Closest in time.