Search Results for author:
Found 12 papers, 5 papers with code
Adversarial Medical Image with Hierarchical Feature Hiding
Interestingly, this vulnerability is a double-edged sword, which can be exploited to hide AEs.
Trainable Projected Gradient Method for Robust Fine-tuning
To solve this problem, we propose Trainable Projected Gradient Method (TPGM) to automatically learn the constraint imposed for each layer for a fine-grained fine-tuning regularization.
Medical Aegis: Robust adversarial protectors for medical images
To the best of our knowledge, Medical Aegis is the first defense in the literature that successfully addresses the strong adaptive adversarial example attacks to medical images.
CloudShield: Real-time Anomaly Detection in the Cloud
Once an anomaly is detected, to reduce alert fatigue, CloudShield automatically distinguishes between benign programs, known attacks, and zero-day attacks, by examining the prediction error distributions.
Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support
Impostors are attackers who take over a smartphone and gain access to the legitimate user's confidential and private information.
ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components.
A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks
Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making.
Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection
A comprehensive evaluation on a public dataset for cephalometric landmark detection demonstrates that the adversarial examples generated by ATI-FGSM break the CNN-based network more effectively and efficiently, compared with the original Iterative FGSM attack.
Sensitive-Sample Fingerprinting of Deep Neural Networks
Numerous cloud-based services are provided to help customers develop and deploy deep learning applications.
VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting
Even small weight changes can be clearly reflected in the model outputs, and observed by the customer.
Privacy-preserving Machine Learning through Data Obfuscation
While it is prevalent to outsource model training and serving tasks in the cloud, it is important to protect the privacy of sensitive samples in the training dataset and prevent information leakage to untrusted third parties.
Power-Grid Controller Anomaly Detection with Enhanced Temporal Deep Learning
Specifically, we first train a temporal deep learning model, using only normal HPC readings from legitimate processes that run daily in these power-grid systems, to model the normal behavior of the power-grid controller.
