Search Results for author:
Found 11 papers, 5 papers with code
Catch Me if You Can: Detecting Unauthorized Data Use in Deep Learning Models
MembershipTracker only requires the users to mark a small fraction of data (0. 005% to 0. 1% in proportion to the training set), and it enables the users to reliably detect the unauthorized use of their data (average 0% FPR@100% TPR).
A Method to Facilitate Membership Inference Attacks in Deep Learning Models
Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models.
Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models
As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow.
Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems
We show that the use of ML in medical systems, particularly connected systems that involve interfacing the ML engine with multiple peripheral devices, has security risks that might cause life-threatening damage to a patient's health in case of adversarial interventions.
A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating from both hardware memory and input faults.
Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction
Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model.
Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision
Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driving.
Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks
Therefore, Jujutsu leverages generative adversarial networks (GAN) to perform localized attack recovery by synthesizing the semantic contents of the input that are corrupted by the attacks, and reconstructs a ``clean'' input for correct prediction.
ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems
These attacks, which we call Ripple False Data Injection Attacks (rfdia), use minimal input perturbations to stealthily change the dnn output.
TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
TensorFI is a configurable FI tool that is flexible, easy to use, and portable.
A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns.
