Search Results for author:
Found 6 papers, 3 papers with code
Multi-Trigger Backdoor Attacks: More Triggers, More Threats
Arguably, real-world backdoor attacks can be much more complex, e. g., the existence of multiple adversaries for the same dataset if it is of high value.
End-to-End Anti-Backdoor Learning on Images and Time Series
Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security.
Reconstructive Neuron Pruning for Backdoor Defense
Specifically, RNP first unlearns the neurons by maximizing the model's error on a small subset of clean samples and then recovers the neurons by minimizing the model's error on the same data.
Anti-Backdoor Learning: Training Clean Models on Poisoned Data
From this view, we identify two inherent characteristics of backdoor attacks as their weaknesses: 1) the models learn backdoored data much faster than learning with clean data, and the stronger the attack the faster the model converges on backdoored data; 2) the backdoor task is tied to a specific class (the backdoor target class).
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
NAD utilizes a teacher network to guide the finetuning of the backdoored student network on a small clean subset of data such that the intermediate-layer attention of the student network aligns with that of the teacher network.
Large Spectral Density Matrix Estimation by Thresholding
Spectral density matrix estimation of multivariate time series is a classical problem in time series and signal processing.
