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 61–70 of 492 papers

TitleStatusHype
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution—0
Attacks on the neural network and defense methods—0
Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning—0
From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security—0
One Pixel is All I Need—0
BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks—0
Deep Learning Model Security: Threats and Defenses—0
Learning to Forget using Hypernetworks—0
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models—0
Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era—0
Show:102550
← PrevPage 7 of 50Next →

No leaderboard results yet.