
Achieving RealTime Execution of 3D Convolutional Neural Networks on Mobile Devices
Mobile devices are becoming an important carrier for deep learning tasks...
read it

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness
Mode connectivity provides novel geometric insights on analyzing loss la...
read it

Towards RealTime DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization
Highend mobile platforms rapidly serve as primary computing devices for...
read it

MultiPerson Pose Estimation with Enhanced Feature Aggregation and Selection
We propose a novel Enhanced Feature Aggregation and Selection network (E...
read it

A PrivacyPreserving DNN Pruning and Mobile Acceleration Framework
To facilitate the deployment of deep neural networks (DNNs) on resource...
read it

Security of Deep Learning based Lane Keeping System under PhysicalWorld Adversarial Attack
LaneKeeping Assistance System (LKAS) is convenient and widely available...
read it

Automatic Perturbation Analysis on General Computational Graphs
Linear relaxation based perturbation analysis for neural networks, which...
read it

Defending against Backdoor Attack on Deep Neural Networks
Although deep neural networks (DNNs) have achieved a great success in va...
read it

Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
Graph Neural Networks (GNNs) have made significant advances on several f...
read it

AdvMS: A Multisource Multicost Defense Against Adversarial Attacks
Designing effective defense against adversarial attacks is a crucial top...
read it

RTMobile: Beyond RealTime Mobile Acceleration of RNNs for Speech Recognition
Recurrent neural networks (RNNs) based automatic speech recognition has ...
read it

Block Switching: A Stochastic Approach for Deep Learning Security
Recent study of adversarial attacks has revealed the vulnerability of mo...
read it

Towards QueryEfficient BlackBox Adversary with ZerothOrder Natural Gradient Descent
Despite the great achievements of the modern deep neural networks (DNNs)...
read it

BLKREW: A Unified Blockbased DNN Pruning Framework using Reweighted Regularization Method
Accelerating DNN execution on various resourcelimited computing platfor...
read it

PatDNN: Achieving RealTime DNN Execution on Mobile Devices with Patternbased Weight Pruning
With the emergence of a spectrum of highend mobile devices, many applic...
read it

Evading RealTime Person Detectors by Adversarial Tshirt
It is known that deep neural networks (DNNs) could be vulnerable to adve...
read it

ZOAdaMM: ZerothOrder Adaptive Momentum Method for BlackBox Optimization
The adaptive momentum method (AdaMM), which uses past gradients to updat...
read it

Reweighted Proximal Pruning for LargeScale Language Representation
Recently, pretrained language representation flourishes as the mainstay...
read it

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Realtime Execution on Mobile Devices
Model compression techniques on Deep Neural Network (DNN) have been wide...
read it

Protecting Neural Networks with Hierarchical Random Switching: Towards Better RobustnessAccuracy Tradeoff for Stochastic Defenses
Despite achieving remarkable success in various domains, recent studies ...
read it

On the Design of Blackbox Adversarial Examples by Leveraging Gradientfree Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics wh...
read it

Nonstructured DNN Weight Pruning Considered Harmful
Large deep neural network (DNN) models pose the key challenge to energy ...
read it

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to gra...
read it

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
Despite the great achievements of deep neural networks (DNNs), the vulne...
read it

Interpreting Adversarial Examples by Activation Promotion and Suppression
It is widely known that convolutional neural networks (CNNs) are vulnera...
read it

Second Rethinking of Network Pruning in the Adversarial Setting
It is well known that deep neural networks (DNNs) are vulnerable to adve...
read it

Progressive DNN Compression: A Key to Achieve UltraHigh Weight Pruning and Quantization Rates using ADMM
Weight pruning and weight quantization are two important categories of D...
read it

ADMMNN: An AlgorithmHardware CoDesign Framework of DNNs Using Alternating Direction Method of Multipliers
To facilitate efficient embedded and hardware implementations of deep ne...
read it

ERNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
Recurrent Neural Networks (RNNs) are becoming increasingly important for...
read it

A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
Many model compression techniques of Deep Neural Networks (DNNs) have be...
read it

Progressive Weight Pruning of Deep Neural Networks using ADMM
Deep neural networks (DNNs) although achieving humanlevel performance i...
read it

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
Deep neural networks (DNNs) are known vulnerable to adversarial attacks....
read it

Structured Adversarial Attack: Towards General Implementation and Better Interpretability
When generating adversarial examples to attack deep neural networks (DNN...
read it

ADAMADMM: A Unified, Systematic Framework of Structured Weight Pruning for DNNs
Weight pruning methods of deep neural networks (DNNs) have been demonstr...
read it

An ADMMBased Universal Framework for Adversarial Attacks on Deep Neural Networks
Deep neural networks (DNNs) are known vulnerable to adversarial attacks....
read it

PredictionBased Fast Thermoelectric Generator Reconfiguration for Energy Harvesting from Vehicle Radiators
Thermoelectric generation (TEG) has increasingly drawn attention for bei...
read it

On the Universal Approximation Property and Equivalence of Stochastic Computingbased Neural Networks and Binary Neural Networks
Largescale deep neural networks are both memory intensive and computati...
read it

Towards UltraHigh Performance and Energy Efficiency of Deep Learning Systems: An AlgorithmHardware CoOptimization Framework
Hardware accelerations of deep learning systems have been extensively in...
read it

CirCNN: Accelerating and Compressing Deep Neural Networks Using BlockCirculantWeight Matrices
Largescale deep neural networks (DNNs) are both compute and memory inte...
read it
Xue Lin
is this you? claim profile