Search Results for author:
Found 19 papers, 10 papers with code
Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
State-of-the-art techniques for enhancing robustness of deep networks mostly rely on empirical risk minimization with suitable data augmentation.
Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations
While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control over, the features being extracted.
Self-supervised Speaker Recognition Training Using Human-Machine Dialogues
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication.
Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing
We derive the worst-case attack for the GLRT defense, and show that its asymptotic performance (as the dimension of the data increases) approaches that of the minimax defense.
All-Digital LoS MIMO with Low-Precision Analog-to-Digital Conversion
Line-of-sight (LoS) multi-input multi-output (MIMO) systems exhibit attractive scaling properties with increase in carrier frequency: for a fixed form factor and range, the spatial degrees of freedom increase quadratically for 2D arrays, in addition to the typically linear increase in available bandwidth.
Sparse Coding Frontend for Robust Neural Networks
Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations.
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations
Our nominal design is to train the decoder and classifier together in standard supervised fashion, but we also consider unsupervised decoder training based on a regression objective (as in a conventional autoencoder) with separate supervised training of the classifier.
Adversarially Robust Classification based on GLRT
We evaluate the GLRT approach for the special case of binary hypothesis testing in white Gaussian noise under $\ell_{\infty}$ norm-bounded adversarial perturbations, a setting for which a minimax strategy optimizing for the worst-case attack is known.
Multi-sensor Spatial Association using Joint Range-Doppler Features
We investigate the problem of localizing multiple targets using a single set of measurements from a network of radar sensors.
Wireless Fingerprinting via Deep Learning: The Impact of Confounding Factors
The opportunity for doing so arises due to subtle nonlinear variations across transmitters, even those made by the same manufacturer.
Polarizing Front Ends for Robust CNNs
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their "excessive linearity."
A design framework for all-digital mmWave massive MIMO with per-antenna nonlinearities
Millimeter wave MIMO combines the benefits of compact antenna arrays with a large number of elements and massive bandwidths, so that fully digital beamforming has the potential of supporting a large number of simultaneous users with {\it per user} data rates of multiple gigabits/sec (Gbps).
Robust Wireless Fingerprinting via Complex-Valued Neural Networks
A "wireless fingerprint" which exploits hardware imperfections unique to each device is a potentially powerful tool for wireless security.
Robust Adversarial Learning via Sparsifying Front Ends
We also devise attacks based on the locally linear model that outperform the well-known FGSM attack.
Combating Adversarial Attacks Using Sparse Representations
It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs).
On the information in spike timing: neural codes derived from polychronous groups
There is growing evidence regarding the importance of spike timing in neural information processing, with even a small number of spikes carrying information, but computational models lag significantly behind those for rate coding.
Sparsity-based Defense against Adversarial Attacks on Linear Classifiers
In this paper, we study this phenomenon in the setting of a linear classifier, and show that it is possible to exploit sparsity in natural data to combat $\ell_{\infty}$-bounded adversarial perturbations.
Learning Sparse, Distributed Representations using the Hebbian Principle
The "fire together, wire together" Hebbian model is a central principle for learning in neuroscience, but surprisingly, it has found limited applicability in modern machine learning.
Compressive spectral embedding: sidestepping the SVD
Spectral embedding based on the Singular Value Decomposition (SVD) is a widely used "preprocessing" step in many learning tasks, typically leading to dimensionality reduction by projecting onto a number of dominant singular vectors and rescaling the coordinate axes (by a predefined function of the singular value).
