data-poisoning

There are 1 repository under data-poisoning topic.

RiccardoBiosas / awesome-MLSecOps
A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.
data-poisoning exploit large-language-models llm machine-learning mlops mlsecops prompt prompt-engineering security cloud devsecops machine-learning-security awesome
176
penghui-yang / awesome-data-poisoning-and-backdoor-attacks
A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them
awesome-list backdoor-attacks backdoor-defense data-poisoning machine-learning
133
ZhengyuZhao / AI-Security-and-Privacy-Events
A curated list of academic events on AI Security & Privacy
adversarial-examples adversarial-machine-learning ai-privacy ai-security data-poisoning
117
TLMichael / Delusive-Adversary
[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
adversarial-training data-poisoning delusive-attacks deep-learning
Language:Python 31
kaiwenzha / contrastive-poisoning
[ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
contrastive-learning data-poisoning iclr iclr-2023 representation-learning adversarial-machine-learning robustness adversarial-attacks
Language:Python 25
ch-shin / awesome-data-poisoning
awesome awesome-list awesome-lists data-poisoning data-poisoning-attacks backdoor-attacks robust-learning
19
lafeat / apbench
APBench: A Unified Availability Poisoning Attack and Defenses Benchmark
adversarial-attacks adversarial-machine-learning availability-poisoning data-poisoning unlearnable-examples
Language:Python 16
ruoxi-jia-group / Meta-Sift
The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on poisoned dataset.
ai-security backdoor-attacks data-poisoning dataset-security
Language:Python 14
akshaymehra24 / PoisoningCertifiedDefenses
How Robust are Randomized Smoothing based Defenses to Data Poisoning? (CVPR 2021)
attack data-poisoning gaussian-data-augmentation randomized-smoothing robust-training-procedures
Language:Python 11
Fraunhofer-AISEC / regression-data-poisoning
Experiments on Data Poisoning Regression Learning
regression-learning data-poisoning-attacks data-poisoning adversarial-machine-learning
Language:Python 11
liuzrcc / ImageShortcutSqueezing
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
availability-poisoning data-poisoning unlearnable-examples
Language:Python 11
bliutech / SeBRUS
Accepted to MIT IEEE URTC 2023. GSET 2023. Repository for "SeBRUS: Mitigating Data Poisoning in Crowdsourced Datasets with Blockchain".
data-poisoning ethereum python-flask reactjs solidity
Language:JavaScript 8
akshaymehra24 / LimitsOfUDA
Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning. (Neurips 2021)
data-poisoning domain-adaptation unsupervised-domain-adaptation
Language:Python 7
ZaydH / target_identification
CCS'22 Paper: "Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation"
backdoor-attacks data-poisoning
Language:Python 7
andrea-gasparini / backdoor-federated-learning
A backdoor attack in a Federated learning setting using the FATE framework
backdoor-attacks federated-learning fate data-poisoning-attacks data-poisoning machine-learning-attack
Language:Python 6
mithridates
ebagdasa / mithridates
Measure and Boost Backdoor Robustness
ai-safety backdoor-attacks backdoor-resistance data-poisoning hyperparameter-tuning ml-defenses ml-security robustness
Language:Jupyter Notebook 6
privacytrustlab / adversarial_bias
Analyzing Adversarial Bias and the Robustness of Fair Machine Learning
machine-learning algorithmic-fairness bias robustness data-poisoning
Language:Python 6
rssalessio / data-poisoning-linear-systems
Code for the paper Analysis and Detectability of Offline Data Poisoning Attacks on Linear Systems.
analysis data-driven-control data-poisoning detectability dynamical-systems linear-systems python
Language:Python 6
TLMichael / Hypocritical-Perturbation
[NeurIPS 2022] Can Adversarial Training Be Manipulated By Non-Robust Features?
adversarial-training data-poisoning deep-learning delusive-attacks stability-attacks
Language:Python 3
ebegoli / StreamToxWatch
A repository for the experimental framework for in-stream data poisoning monitoring.
data-poisoning
Language:Python

data-poisoning

RiccardoBiosas / awesome-MLSecOps

penghui-yang / awesome-data-poisoning-and-backdoor-attacks

ZhengyuZhao / AI-Security-and-Privacy-Events

TLMichael / Delusive-Adversary

kaiwenzha / contrastive-poisoning

ch-shin / awesome-data-poisoning

lafeat / apbench

ruoxi-jia-group / Meta-Sift

akshaymehra24 / PoisoningCertifiedDefenses

Fraunhofer-AISEC / regression-data-poisoning

liuzrcc / ImageShortcutSqueezing

bliutech / SeBRUS

akshaymehra24 / LimitsOfUDA

ZaydH / target_identification

andrea-gasparini / backdoor-federated-learning

ebagdasa / mithridates

privacytrustlab / adversarial_bias

rssalessio / data-poisoning-linear-systems

TLMichael / Hypocritical-Perturbation

ebegoli / StreamToxWatch