Publications (56)
Processing-In-Memory Acceleration of Convolutional Neural Networks for Energy-Efficiency, and Power-Intermittency Resilience
Arman Roohi, Shaahin Angizi, Deliang Fan +1
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…
Defending Against Adversarial Attacks Using Random Forests
Yifan Ding, Liqiang Wang, Huan Zhang +3
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. Unfortun…
Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation
Zhezhi He, Deliang Fan
In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation…
AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
Yongjae Lee, Jingxing Li, Abhay Kumar Yadav +2
Adaptive density control in 3D Gaussian Splatting (3DGS) repeatedly grows the Gaussian population through fixed-cardinality random splitting to discover useful scene structure. How…
:Dynamic Additive Attention Adaption for Memory-EfficientOn-Device Multi-Domain Learning
Li Yang, Adnan Siraj Rakin, Deliang Fan
Nowadays, one practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). It motivates researchers…
TBT: Targeted Neural Network Attack with Bit Trojan
Adnan Siraj Rakin, Zhezhi He, Deliang Fan
Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently,…
Current Induced Dynamics of Multiple Skyrmions with Domain Wall Pair and Skyrmion-based Majority Gate Design
Zhezhi He, Shaahin Angizi, Deliang Fan
As an intriguing ultra-small particle-like magnetic texture, skyrmion has attracted lots of research interests in next-generation ultra-dense and low power magnetic memory/logic de…
NeurObfuscator: A Full-stack Obfuscation Tool to Mitigate Neural Architecture Stealing
Jingtao Li, Zhezhi He, Adnan Siraj Rakin +2
Neural network stealing attacks have posed grave threats to neural network model deployment. Such attacks can be launched by extracting neural architecture information, such as lay…
TRGP: Trust Region Gradient Projection for Continual Learning
Sen Lin, Li Yang, Deliang Fan +1
Catastrophic forgetting is one of the major challenges in continual learning. To address this issue, some existing methods put restrictive constraints on the optimization space of…
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels
Yifan Ding, Liqiang Wang, Deliang Fan +1
The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dat…
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
Adnan Siraj Rakin, Zhezhi He, Deliang Fan
Recent development in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an ad…
Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers
Mark Horton, Tergel Molom-Ochir, Peter Liu +8
Pre-trained transformer models with extended context windows are notoriously expensive to run at scale, often limiting real-world deployment due to their high computational and mem…
Design and Synthesis of Ultra Low Energy Spin-Memristor Threshold Logic
Deliang Fan, Mrigank Sharad, Kaushik Roy
A threshold logic gate (TLG) performs weighted sum of multiple inputs and compares the sum with a threshold. We propose Spin-Memeristor Threshold Logic (SMTL) gates, which employ m…
Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
Li Yang, Sen Lin, Fan Zhang +2
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 le…
T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Adnan Siraj Rakin, Zhezhi He, Jingtao Li +3
Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, atta…
KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning
Li Yang, Zhezhi He, Junshan Zhang +1
Deep Neural Networks (DNN) could forget the knowledge about earlier tasks when learning new tasks, and this is known as \textit{catastrophic forgetting}. While recent continual lea…
Energy-Efficient and Robust Associative Computing with Electrically Coupled Dual Pillar Spin-Torque Oscillators
Mrigank Sharad, Deliang Fan, Karthik Yogendra +1
Dynamics of coupled spin-torque oscillators can be exploited for non-Boolean information processing. However, the feasibility of coupling large number of STOs with energy-efficienc…
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Adnan Siraj Rakin, Li Yang, Jingtao Li +5
Recently developed adversarial weight attack, a.k.a. bit-flip attack (BFA), has shown enormous success in compromising Deep Neural Network (DNN) performance with an extremely small…
DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
Fan Yao, Adnan Siraj Rakin, Deliang Fan
Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have…
Model Extraction Attacks on Split Federated Learning
Jingtao Li, Adnan Siraj Rakin, Xing Chen +4
Federated Learning (FL) is a popular collaborative learning scheme involving multiple clients and a server. FL focuses on protecting clients' data but turns out to be highly vulner…
Representable Matrices: Enabling High Accuracy Analog Computation for Inference of DNNs using Memristors
Baogang Zhang, Necati Uysal, Deliang Fan +1
Analog computing based on memristor technology is a promising solution to accelerating the inference phase of deep neural networks (DNNs). A fundamental problem is to map an arbitr…
Gradient-based Novelty Detection Boosted by Self-supervised Binary Classification
Jingbo Sun, Li Yang, Jiaxin Zhang +4
Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them. It is a critical step in data monitoring, behavior analysis an…
TFL: Targeted Bit-Flip Attack on Large Language Model
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection atta…
GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularization
Jingxing Li, Yongjae Lee, Deliang Fan
Prior ReLoc3R achieves breakthrough performance with fast 25ms inference and state-of-the-art regression accuracy, yet our analysis reveals subtle geometric inconsistencies in its…
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Zhezhi He, Boqing Gong, Deliang Fan
Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become t…
Ultra Low Power Associative Computing with Spin Neurons and Resistive Crossbar Memory
Mrigank Sharad, Deliang Fan, Kaushik Roy
Emerging resistive-crossbar memory (RCM) technology can be promising for computationally-expensive analog pattern-matching tasks. However, the use of CMOS analog-circuits with RCM…
GROWN: GRow Only When Necessary for Continual Learning
Li Yang, Sen Lin, Junshan Zhang +1
Catastrophic forgetting is a notorious issue in deep learning, referring to the fact that Deep Neural Networks (DNN) could forget the knowledge about earlier tasks when learning ne…
Exploring Boolean and Non-Boolean Computing Applications of Spin Torque Devices
Kaushik Roy, Mrigank Sharad, Deliang Fan +1
In this paper we discuss the potential of emerging spintorque devices for computing applications. Recent proposals for spinbased computing schemes may be differentiated as all-spin…
Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions
Adnan Siraj Rakin, Jinfeng Yi, Boqing Gong +1
Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNN…
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples
Adnan Siraj Rakin, Zhezhi He, Boqing Gong +1
Deep learning algorithms and networks are vulnerable to perturbed inputs which is known as the adversarial attack. Many defense methodologies have been investigated to defend again…
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Adnan Siraj Rakin, Yukui Luo, Xiaolin Xu +1
The wide deployment of Deep Neural Networks (DNN) in high-performance cloud computing platforms brought to light multi-tenant cloud field-programmable gate arrays (FPGA) as a popul…
MetaGater: Fast Learning of Conditional Channel Gated Networks via Federated Meta-Learning
Sen Lin, Li Yang, Zhezhi He +2
While deep learning has achieved phenomenal successes in many AI applications, its enormous model size and intensive computation requirements pose a formidable challenge to the dep…
Hierarchical Temporal Memory Based on Spin-Neurons and Resistive Memory for Energy-Efficient Brain-Inspired Computing
Deliang Fan, Mrigank Sharad, Abhronil Sengupta +1
Hierarchical temporal memory (HTM) tries to mimic the computing in cerebral-neocortex. It identifies spatial and temporal patterns in the input for making inferences. This may requ…
Ultra-low Energy, High Performance and Programmable Magnetic Threshold Logic
Mrigank Sharad, Deliang Fan, Kaushik Roy
We propose magnetic threshold-logic (MTL) design based on non-volatile spin-torque switches. A threshold logic gate (TLG) performs summation of multiple inputs multiplied by a fixe…
PANDA: Processing-in-MRAM Accelerated De Bruijn Graph based DNA Assembly
Shaahin Angizi, Naima Ahmed Fahmi, Wei Zhang +1
Spurred by widening gap between data processing speed and data communication speed in Von-Neumann computing architectures, some bioinformatic applications have harnessed the comput…
A Progressive Sub-Network Searching Framework for Dynamic Inference
Li Yang, Zhezhi He, Yu Cao +1
Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dyn…
STT-SNN: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks
Deliang Fan, Yong Shim, Anand Raghunathan +1
Recent years have witnessed growing interest in the use of Artificial Neural Networks (ANNs) for vision, classification, and inference problems. An artificial neuron sums N weighte…
Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
Wanhao Yu, Ziyan Wang, Zheng Wang +7
Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distr…
ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Jingtao Li, Adnan Siraj Rakin, Xing Chen +3
This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL is a recent distributed training scheme where multiple clients send intermediate activat…
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Zhaoliang Zhang, Tianchen Song, Yongjae Lee +4
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. However, as a…
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?
Xiaolong Ma, Sheng Lin, Shaokai Ye +10
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or S…
DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Adnan Siraj Rakin, Md Hafizul Islam Chowdhuryy, Fan Yao +1
Recent advancements of Deep Neural Networks (DNNs) have seen widespread deployment in multiple security-sensitive domains. The need of resource-intensive training and use of valuab…
MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table
Yongjae Lee, Li Yang, Deliang Fan
Neural radiance field (NeRF) has shown remarkable performance in generating photo-realistic novel views. Among recent NeRF related research, the approaches that involve the utiliza…
SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
Jingxing Li, Yongjae Lee, Deliang Fan
3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians, yet its training remains expensive, with the backward pass dom…
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness
Adnan Siraj Rakin, Zhezhi He, Li Yang +3
Deep Neural Network (DNN) trained by the gradient descent method is known to be vulnerable to maliciously perturbed adversarial input, aka. adversarial attack. As one of the counte…
Accelerating Bulk Bit-Wise X(N)OR Operation in Processing-in-DRAM Platform
Shaahin Angizi, Deliang Fan
With Von-Neumann computing architectures struggling to address computationally- and memory-intensive big data analytic task today, Processing-in-Memory (PIM) platforms are gaining…
Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search
Adnan Siraj Rakin, Zhezhi He, Deliang Fan
Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components. The most widely investigated securit…
Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
Sen Lin, Li Yang, Deliang Fan +1
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 k…
Ultra-low Energy, High-Performance Dynamic Resistive Threshold Logic
Mrigank Sharad, Deliang Fan, Kaushik Roy
We propose dynamic resistive threshold-logic (DRTL) design based on non-volatile resistive memory. A threshold logic gate (TLG) performs summation of multiple inputs multiplied by…
SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction
Yongjae Lee, Zhaoliang Zhang, Deliang Fan
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis. However, its suboptimal densification process results in the excessively large number of Gaussian…
CAMformer: Associative Memory is All You Need
Tergel Molom-Ochir, Benjamin F. Morris, Mark Horton +8
Transformers face scalability challenges due to the quadratic cost of attention, which involves dense similarity computations between queries and keys. We propose CAMformer, a nove…
SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Model integrity of Large language models (LLMs) has become a pressing security concern with their massive online deployment. Prior Bit-Flip Attacks (BFAs) -- a class of popular AI…
MERAM: Non-Volatile Cache Memory Based on Magneto-Electric FETs
Shaahin Angizi, Navid Khoshavi, Andrew Marshall +2
Magneto-Electric FET (MEFET) is a recently developed post-CMOS FET, which offers intriguing characteristics for high speed and low-power design in both logic and memory application…
Speedy MASt3R
Jingxing Li, Yongjae Lee, Abhay Kumar Yadav +3
Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization. MASt3R redefines image matching as a 3D task by leve…
RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Jingtao Li, Adnan Siraj Rakin, Zhezhi He +2
Adversarial attacks on Neural Network weights, such as the progressive bit-flip attack (PBFA), can cause a catastrophic degradation in accuracy by flipping a very small number of b…
Developing All-Skyrmion Spiking Neural Network
Zhezhi He, Deliang Fan
In this work, we have proposed a revolutionary neuromorphic computing methodology to implement All-Skyrmion Spiking Neural Network (AS-SNN). Such proposed methodology is based on o…