Search Results for author:
Found 10 papers, 5 papers with code
Generating Natural Language Adversarial Examples
Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify.
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches.
Deep Residual Neural Networks for Audio Spoofing Detection
Additionally, replay attacks where the attacker uses a speaker to replay a previously recorded genuine human speech are also possible.
Did you hear that? Adversarial Examples Against Automatic Speech Recognition
Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
CAAD 2018: Generating Transferable Adversarial Examples
Our team participated in the CAAD 2018 competition, and won 1st place in both attack subtracks, non-targeted and targeted adversarial attacks, and 3rd place in defense.
SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation
second, we use another LSTM network based discriminator model for distinguishing between the true and the synthesized data.
NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning
When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model.
NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
NeuronInspect first identifies the existence of backdoor attack targets by generating the explanation heatmap of the output layer.
Mondegreen: A Post-Processing Solution to Speech Recognition Error Correction for Voice Search Queries
As more and more online search queries come from voice, automatic speech recognition becomes a key component to deliver relevant search results.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
PhysioGAN: Training High Fidelity Generative Model for Physiological Sensor Readings
Generative models such as the variational autoencoder (VAE) and the generative adversarial networks (GAN) have proven to be incredibly powerful for the generation of synthetic data that preserves statistical properties and utility of real-world datasets, especially in the context of image and natural language text.
