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 151–200 of 492 papers

TitleStatusHype
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors—0
Purifying Large Language Models by Ensembling a Small Language Model—0
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based AgentsCode2
SusFL: Energy-Aware Federated Learning-based Monitoring for Sustainable Smart Farms—0
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems—0
The Effect of Data Poisoning on Counterfactual ExplanationsCode0
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language ModelsCode2
Game-Theoretic Unlearnable Example GeneratorCode0
Security and Privacy Challenges of Large Language Models: A Survey—0
Federated Learning with Dual Attention for Robust Modulation Classification under Attacks—0
A GAN-based data poisoning framework against anomaly detection in vertical federated learning—0
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline—0
Data-Dependent Stability Analysis of Adversarial Training—0
Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space—0
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection—0
Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It—0
Balancing Privacy, Robustness, and Efficiency in Machine Learning—0
Progressive Poisoned Data Isolation for Training-time Backdoor DefenseCode0
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning—0
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited KnowledgeCode1
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey—0
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks—0
FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks—0
Mendata: A Framework to Purify Manipulated Training Data—0
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 4 of 10Next →

No leaderboard results yet.