Ластанған деректер
material
ID: poisoneddata
Related Papers
Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
AbstractThis paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a ‘backdoor poisoning’ attack on NLP models. Our poisoning attack utilizes …...
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks
AbstractBackdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give …...
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
AbstractBackdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and …...