Search Results for author:
Found 36 papers, 11 papers with code
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed.
SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis.
MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table
Neural radiance field (NeRF) has shown remarkable performance in generating photo-realistic novel views.
Model Extraction Attacks on Split Federated Learning
We show that under practical cases, the proposed ME attacks work exceptionally well for SFL.
Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially, giving rise to a new paradigm, namely self-supervised continual learning (SSCL).
Get More at Once: Alternating Sparse Training with Gradient Correction
In this work, for the first time, we propose a novel alternating sparse training (AST) scheme to train multiple sparse sub-nets for dynamic inference without extra training cost compared to the case of training a single sparse model from scratch.
Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
By learning a sequence of tasks continually, an agent in continual learning (CL) can improve the learning performance of both a new task and `old' tasks by leveraging the forward knowledge transfer and the backward knowledge transfer, respectively.
ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
While such a scheme helps reduce the computational load at the client end, it opens itself to reconstruction of raw data from intermediate activation by the server.
TRGP: Trust Region Gradient Projection for Continual Learning
To tackle this challenge, we propose Trust Region Gradient Projection (TRGP) for continual learning to facilitate the forward knowledge transfer based on an efficient characterization of task correlation.
Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning
Contrastive learning (or its variants) has recently become a promising direction in the self-supervised learning domain, achieving similar performance as supervised learning with minimum fine-tuning.
Rep-Net: Efficient On-Device Learning via Feature Reprogramming
To develop memory-efficient on-device transfer learning, in this work, we are the first to approach the concept of transfer learning from a new perspective of intermediate feature reprogramming of a pre-trained model (i. e., backbone).
DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Secondly, we propose a novel substitute model training algorithm with Mean Clustering weight penalty, which leverages the partial leaked bit information effectively and generates a substitute prototype of the target victim model.
GROWN: GRow Only When Necessary for Continual Learning
To address this issue, continual learning has been developed to learn new tasks sequentially and perform knowledge transfer from the old tasks to the new ones without forgetting.
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Apart from recovering the inference accuracy, our RA-BNN after growing also shows significantly higher resistance to BFA.
RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
In this work, we propose RADAR, a Run-time adversarial weight Attack Detection and Accuracy Recovery scheme to protect DNN weights against PBFA.
$DA^3$:Dynamic Additive Attention Adaption for Memory-EfficientOn-Device Multi-Domain Learning
We observe that large memory used for activation storage is the bottleneck that largely limits the training time and cost on edge devices.
MetaGater: Fast Learning of Conditional Channel Gated Networks via Federated Meta-Learning
In this work, we advocate a holistic approach to jointly train the backbone network and the channel gating which enables dynamical selection of a subset of filters for more efficient local computation given the data input.
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Specifically, she can aggressively overload the shared power distribution system of FPGA with malicious power-plundering circuits, achieving adversarial weight duplication (AWD) hardware attack that duplicates certain DNN weight packages during data transmission between off-chip memory and on-chip buffer, to hijack the DNN function of the victim tenant.
KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning
Thus motivated, we propose a new training method called \textit{kernel-wise Soft Mask} (KSM), which learns a kernel-wise hybrid binary and real-value soft mask for each task, while using the same backbone model.
A Progressive Sub-Network Searching Framework for Dynamic Inference
Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently.
T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory.
DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains.
Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors
In this paper, a technique that aims to produce the correct output for every input vector is proposed, which involves specifying the memristor conductance values and a scaling factor realized by the peripheral circuitry.
TBT: Targeted Neural Network Attack with Bit Trojan
However, when the attacker activates the trigger by embedding it with any input, the network is forced to classify all inputs to a certain target class.
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?
Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structrued pruning is not competitive in terms of both storage and computation efficiency.
Defending Against Adversarial Attacks Using Random Forests
As deep neural networks (DNNs) have become increasingly important and popular, the robustness of DNNs is the key to the safety of both the Internet and the physical world.
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness
In this work, we show that shrinking the model size through proper weight pruning can even be helpful to improve the DNN robustness under adversarial attack.
Processing-In-Memory Acceleration of Convolutional Neural Networks for Energy-Efficiency, and Power-Intermittency Resilience
Herein, a bit-wise Convolutional Neural Network (CNN) in-memory accelerator is implemented using Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) computational sub-arrays.
Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search
Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components.
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation.
Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation
In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications.
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Deep convolution neural network has achieved great success in many artificial intelligence applications.
Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks.
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
In the first stage, we identify a small portion of images from the noisy training set of which the labels are correct with a high probability.
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples
Blind pre-processing improves the white box attack accuracy of MNIST from 94. 3\% to 98. 7\%.
Developing All-Skyrmion Spiking Neural Network
In this work, we have proposed a revolutionary neuromorphic computing methodology to implement All-Skyrmion Spiking Neural Network (AS-SNN).
