Search Results for author:
Found 6 papers, 0 papers with code
Scalable privacy-preserving cancer type prediction with homomorphic encryption
Privacy concerns in outsourced ML, especially in the field of genetics, motivate the use of encrypted computation, like Homomorphic Encryption (HE).
PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks
Based on our theoretical analysis and experimental results, we demonstrate the effectiveness of PiDAn in defending against backdoor attacks that use different settings of poisoned samples on GTSRB and ILSVRC2012 datasets.
TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis
Using a real-world cancer dataset, we analyze the dataset with the bias that already existed towards white individuals and also introduced biases in datasets artificially, and our experimental result show that TRAPDOOR can detect the presence of dataset bias with 100% accuracy, and furthermore can also extract the extent of bias by recovering the percentage with a small error.
Explainability Matters: Backdoor Attacks on Medical Imaging
Extensive evaluation of a state-of-the-art architecture demonstrates that by introducing images with few-pixel perturbations into the training set, an attacker can execute the backdoor successfully without having to be involved with the training procedure.
FaceHack: Triggering backdoored facial recognition systems using facial characteristics
In this work, we demonstrate that specific changes to facial characteristics may also be used to trigger malicious behavior in an ML model.
Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-based Traffic Congestion Control Systems
We develop a trigger design methodology that is based on well-established principles of traffic physics.
