SOTAVerified

Data Poisoning

Data Poisoning is an adversarial attack that tries to manipulate the training dataset in order to control the prediction behavior of a trained model such that the model will label malicious examples into a desired classes (e.g., labeling spam e-mails as safe).

Source: Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–350 of 492 papers

TitleStatusHype
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning—0
Data Poisoning Attack Aiming the Vulnerability of Continual Learning—0
Backdoor Vulnerabilities in Normally Trained Deep Learning Models—0
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners—0
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical SystemsCode0
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain—0
Try to Avoid Attacks: A Federated Data Sanitization Defense for Healthcare IoMT Systems—0
FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification—0
Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario—0
Training set cleansing of backdoor poisoning by self-supervised representation learning—0
Detecting Backdoors in Deep Text Classifiers—0
On Optimal Learning Under Targeted Data Poisoning—0
Understanding Influence Functions and Datamodels via Harmonic Analysis—0
On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based ApproachCode0
Defend Data Poisoning Attacks on Voice Authentication—0
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning—0
Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithm—0
Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System—0
Neural network fragile watermarking with no model performance degradation—0
Lethal Dose Conjecture on Data PoisoningCode0
Testing the Robustness of Learned Index StructuresCode0
Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications—0
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain—0
Backdoor Attack is a Devil in Federated GAN-based Medical Image SynthesisCode0
Efficient Reward Poisoning Attacks on Online Deep Reinforcement LearningCode0
BagFlip: A Certified Defense against Data PoisoningCode0
SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning—0
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning—0
Federated Multi-Armed Bandits Under Byzantine Attacks—0
VPN: Verification of Poisoning in Neural Networks—0
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning—0
GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV—0
Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy—0
Indiscriminate Data Poisoning Attacks on Neural NetworksCode0
Breaking Fair Binary Classification with Optimal Flipping Attacks—0
Machine Learning Security against Data Poisoning: Are We There Yet?Code0
Robustly-reliable learners under poisoning attacks—0
Targeted Data Poisoning Attack on News Recommendation System by Content Perturbation—0
Poisoning Attacks and Defenses on Artificial Intelligence: A Survey—0
Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy—0
Collaborative Self Organizing Map with DeepNNs for Fake Task Prevention in Mobile Crowdsensing—0
An Equivalence Between Data Poisoning and Byzantine Gradient AttacksCode0
Redactor: A Data-centric and Individualized Defense Against Inference Attacks—0
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite AggregationCode0
Towards Multi-Objective Statistically Fair Federated Learning—0
How to Backdoor HyperNetwork in Personalized Federated Learning?—0
Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of RobustnessCode0
Compression-Resistant Backdoor Attack against Deep Neural Networks—0
Execute Order 66: Targeted Data Poisoning for Reinforcement Learning—0
ML Attack Models: Adversarial Attacks and Data Poisoning Attacks—0
Show:102550
← PrevPage 7 of 10Next →

No leaderboard results yet.