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 311–320 of 492 papers

TitleStatusHype
Training set cleansing of backdoor poisoning by self-supervised representation learning—0
Data Poisoning Attack Aiming the Vulnerability of Continual Learning—0
Model-Agnostic Explanations using Minimal Forcing Subsets—0
TrojanTime: Backdoor Attacks on Time Series Classification—0
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning—0
Try to Avoid Attacks: A Federated Data Sanitization Defense for Healthcare IoMT Systems—0
Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training—0
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks—0
Understanding Influence Functions and Datamodels via Harmonic Analysis—0
Unlearnable Examples Detection via Iterative Filtering—0
Show:102550
← PrevPage 32 of 50Next →

No leaderboard results yet.