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 176–200 of 492 papers

TitleStatusHype
Universal Backdoor AttacksCode0
IMMA: Immunizing text-to-image Models against Malicious AdaptationCode1
Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective—0
Trainwreck: A damaging adversarial attack on image classifiersCode0
Security and Privacy Challenges in Deep Learning Models—0
BrainWash: A Poisoning Attack to Forget in Continual Learning—0
Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems—0
PACOL: Poisoning Attacks Against Continual Learners—0
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models—0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification—0
Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models—0
PrivacyGAN: robust generative image privacy—0
Histopathological Image Classification and Vulnerability Analysis using Federated Learning—0
Transferable Availability Poisoning AttacksCode0
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksCode0
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning—0
Post-Training Overfitting Mitigation in DNN Classifiers—0
Towards Poisoning Fair Representations—0
Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained ModelsCode0
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning AttacksCode0
CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation—0
Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning AttacksCode1
Systematic Testing of the Data-Poisoning Robustness of KNN—0
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy—0
Show:102550
← PrevPage 8 of 20Next →

No leaderboard results yet.