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 26–50 of 492 papers

TitleStatusHype
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents—0
Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR ImagesCode0
What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift—0
A Geometric Approach to Problems in Optimization and Data Science—0
Investigating cybersecurity incidents using large language models in latest-generation wireless networks—0
ControlNET: A Firewall for RAG-based LLM System—0
Diversity-aware Dual-promotion Poisoning Attack on Sequential Recommendation—0
Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning—0
Data Poisoning in Deep Learning: A SurveyCode1
Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing—0
Optimizing ML Training with Metagradient Descent—0
Policy Teaching via Data Poisoning in Learning from Human Preferences—0
Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification—0
Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models—0
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models—0
Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data—0
Data Poisoning Attacks to Locally Differentially Private Range Query Protocols—0
Approaching the Harm of Gradient Attacks While Only Flipping Labels—0
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data—0
Atlas: A Framework for ML Lifecycle Provenance & Transparency—0
Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs—0
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoningCode0
FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL—0
Multi-Faceted Studies on Data Poisoning can Advance LLM DevelopmentCode0
A Robust Attack: Displacement Backdoor Attack—0
Show:102550
← PrevPage 2 of 20Next →

No leaderboard results yet.