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 426–450 of 492 papers

TitleStatusHype
Data Shifts Hurt CoT: A Theoretical Study—0
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning—0
Deep Learning Model Security: Threats and Defenses—0
Deep Probabilistic Models to Detect Data Poisoning Attacks—0
Defend Data Poisoning Attacks on Voice Authentication—0
Defending against Backdoor Attack on Deep Neural Networks—0
Defending Against Backdoor Attacks Using Ensembles of Weak Learners—0
Defending Backdoor Data Poisoning Attacks by Using Noisy Label Defense Algorithm—0
Defending Against Adversarial Denial-of-Service Data Poisoning Attacks—0
Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy—0
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm—0
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks—0
Detecting Backdoors in Deep Text Classifiers—0
Detection of Physiological Data Tampering Attacks with Quantum Machine Learning—0
Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications—0
Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols—0
Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats—0
Diversity-aware Dual-promotion Poisoning Attack on Sequential Recommendation—0
Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithm—0
Don't Forget What I did?: Assessing Client Contributions in Federated Learning—0
DP-InstaHide: Data Augmentations Provably Enhance Guarantees Against Dataset Manipulations—0
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning—0
Influence-Driven Data Poisoning in Graph-Based Semi-Supervised Classifiers—0
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models—0
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective—0
Show:102550
← PrevPage 18 of 20Next →

No leaderboard results yet.