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 301–325 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
Show:102550
← PrevPage 13 of 20Next →

No leaderboard results yet.