data poisoning
Leaderboards
Greatest papers with code
How To Backdoor Federated Learning
• ebagdasa/backdoor_federated_learning
• 
An attacker selected in a single round of federated learning can cause the global model to immediately reach 100% accuracy on the backdoor task.
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
We utilize trusted data by proposing a loss correction technique that utilizes trusted examples in a data-efficient manner to mitigate the effects of label noise on deep neural network classifiers.
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
NeurIPS 2018
• ashafahi/inceptionv3-transferLearn-poison
• 
The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data.
Radioactive data: tracing through training
• facebookresearch/radioactive_data
•
The mark is robust to strong variations such as different architectures or optimization methods.
MetaPoison: Practical General-purpose Clean-label Data Poisoning
Data poisoning--the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data--is an emerging threat in the context of neural networks.
Stronger Data Poisoning Attacks Break Data Sanitization Defenses
• kohpangwei/data-poisoning-journal-release
•
Can data poisoning attacks break data sanitization defenses?
Penalty Method for Inversion-Free Deep Bilevel Optimization
Bilevel optimization problems are at the center of several important machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, data poisoning.
BILEVEL OPTIMIZATION DATA POISONING DENOISING FEW-SHOT LEARNING OMNIGLOT
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
• Sanghyun-Hong/Gradient-Shaping
• 
In this work, we study the feasibility of an attack-agnostic defense relying on artifacts that are common to all poisoning attacks.
Poisoning Attacks with Generative Adversarial Nets
In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i. e. samples that look like genuine data points but that degrade the classifier's accuracy when used for training.
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
We show empirically that the adversarial examples generated by these attack strategies are quite different from genuine points, as no detectability constrains are considered to craft the attack.
ANOMALY DETECTION DATA POISONING NETWORK INTRUSION DETECTION OUTLIER DETECTION