Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
Wei Li, Pin-Yu Chen, Sijia Liu +1
Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is…
cs.LG2025
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Changchang Sun, Ren Wang, Yihua Zhang +5
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to…
cs.LG2024
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Soumyadeep Pal, Yuguang Yao, Ren Wang +2
Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisonin…