Search Results for author:
Found 46 papers, 7 papers with code
DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems
The proliferation of smartphones and other mobile devices provides a unique opportunity to make Advanced Driver Assistance Systems (ADAS) accessible to everyone in the form of an application empowered by low-cost Machine/Deep Learning (ML/DL) models to enhance road safety.
SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms
This varying performance at some distinct scenarios suggests that designing DL-SLAM algorithms taking operating environments and tasks in consideration can achieve optimal performance and resource efficiency for deployment in resource-constrained embedded platforms.
Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weather
In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge.
Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
We believe a scaled down version of our approach will provide insight into the benefits and pitfalls of using TCA to study continual learning dynamics.
SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications
In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a novel approach designed to comprehensively disrupt monocular depth estimation (MDE) in autonomous navigation applications.
MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices
MedAide achieves 77\% accuracy in medical consultations and scores 56 in USMLE benchmark, enabling an energy-efficient healthcare assistance platform that alleviates privacy concerns due to edge-based deployment, thereby empowering the community.
ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches
ODDR operates through a robust three-stage pipeline: Fragmentation, Segregation, and Neutralization.
A Survey on Quantum Machine Learning: Current Trends, Challenges, Opportunities, and the Road Ahead
Quantum Computing (QC) claims to improve the efficiency of solving complex problems, compared to classical computing.
Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook
Through this comprehensive survey, we aim to provide a valuable resource for researchers, practitioners, and policymakers to gain a holistic understanding of physical adversarial attacks in computer vision and facilitate the development of robust and secure DNN-based systems.
SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation
In this paper, we investigate the vulnerability of MDE to adversarial patches.
Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
The challenging deployment of compute-intensive applications from domains such Artificial Intelligence (AI) and Digital Signal Processing (DSP), forces the community of computing systems to explore new design approaches.
FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization
To address this issue, we propose a novel Fault-Aware Quantization (FAQ) technique for mitigating the effects of stuck-at permanent faults in the on-chip weight memory of DNN accelerators at a negligible overhead cost compared to fault-aware retraining while offering comparable accuracy results.
DAP: A Dynamic Adversarial Patch for Evading Person Detectors
Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems.
eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators
To realize these concepts, in this work, we present a novel framework, eFAT, that computes the resilience of a given DNN to faults at different fault rates and with different levels of retraining, and it uses that knowledge to build a resilience map given a user-defined accuracy constraint.
EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
The key mechanisms of our EnforceSNN are: (1) employing quantized weights to reduce the DRAM access energy; (2) devising an efficient DRAM mapping policy to minimize the DRAM energy-per-access; (3) analyzing the SNN error tolerance to understand its accuracy profile considering different bit error rate (BER) values; (4) leveraging the information for developing an efficient fault-aware training (FAT) that considers different BER values and bit error locations in DRAM to improve the SNN error tolerance; and (5) developing an algorithm to select the SNN model that offers good trade-offs among accuracy, memory, and energy consumption.
RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
Our FAM technique leverages the fault map of SNN compute engine for (i) minimizing weight corruption when mapping weight bits on the faulty memory cells, and (ii) selectively employing faulty neurons that do not cause significant accuracy degradation to maintain accuracy and throughput, while considering the SNN operations and processing dataflow.
Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens
Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if models' hyperparameters have any impact on the privacy/utility trade-off of differentially private models.
AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems
Unlike mask based fake-weather attacks that require access to the underlying computing hardware or image memory, our attack is based on emulating the effects of a natural weather condition (i. e., Raindrops) that can be printed on a translucent sticker, which is externally placed over the lens of a camera.
APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation
APARATE, results in a mean depth estimation error surpassing $0. 5$, significantly impacting as much as $99\%$ of the targeted region when applied to CNN-based MDE models.
CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networks
The high computational complexity of these networks, which translates to increased energy consumption, is the foremost obstacle towards deploying large DNNs in resource-constrained systems.
Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
The real-world use cases of Machine Learning (ML) have exploded over the past few years.
SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors
These errors can change the weight values and neuron operations in the compute engine of SNN accelerators, thereby leading to incorrect outputs and accuracy degradation.
Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation.
ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
Since recent works still focus on the fault-modeling and random fault injection in SNNs, the impact of memory faults in SNN hardware architectures on accuracy and the respective fault-mitigation techniques are not thoroughly explored.
Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks
Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions.
Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks
From tiny pacemaker chips to aircraft collision avoidance systems, the state-of-the-art Cyber-Physical Systems (CPS) have increasingly started to rely on Deep Neural Networks (DNNs).
SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM
The key mechanisms of SparkXD are: (1) improving the SNN error tolerance through fault-aware training that considers bit errors from approximate DRAM, (2) analyzing the error tolerance of the improved SNN model to find the maximum tolerable bit error rate (BER) that meets the targeted accuracy constraint, and (3) energy-efficient DRAM data mapping for the resilient SNN model that maps the weights in the appropriate DRAM location to minimize the DRAM access energy.
DNN-Life: An Energy-Efficient Aging Mitigation Framework for Improving the Lifetime of On-Chip Weight Memories in Deep Neural Network Hardware Architectures
We propose DNN-Life, a specialized aging analysis and mitigation framework for DNNs, which jointly exploits hardware- and software-level knowledge to improve the lifetime of a DNN weight memory with reduced energy overhead.
Quantization
Hardware Architecture
DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware
We analyze the corresponding on-chip memory requirements and leverage it to propose a novel methodology to explore different scratchpad memory designs and their energy/area trade-offs.
DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks
Many convolutional neural network (CNN) accelerators face performance- and energy-efficiency challenges which are crucial for embedded implementations, due to high DRAM access latency and energy.
FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks
With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems.
FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation
In this paper, we perform a comprehensive error resilience analysis of DNNs subjected to hardware faults (e. g., permanent faults) in the weight memory.
ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining
A suitable approximate multiplier is then selected for each computing element from a library of approximate multipliers in such a way that (i) one approximate multiplier serves several layers, and (ii) the overall classification error and energy consumption are minimized.
FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks
The goal is to reduce the hardware requirements of CapsNets by removing unused/redundant connections and capsules, while keeping high accuracy through tests of different learning rate policies and batch sizes.
autoAx: An Automatic Design Space Exploration and Circuit Building Methodology utilizing Libraries of Approximate Components
Because these libraries contain from tens to thousands of approximate implementations for a single arithmetic operation it is intractable to find an optimal combination of approximate circuits in the library even for an application consisting of a few operations.
Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w. r. t.
ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators
Our experimental results show that the ROMANet saves DRAM access energy by 12% for the AlexNet, by 36% for the VGG-16, and by 46% for the MobileNet, while also improving the DRAM throughput by 10%, as compared to the state-of-the-art.
CapStore: Energy-Efficient Design and Management of the On-Chip Memory for CapsuleNet Inference Accelerators
By leveraging this analysis, we propose a methodology to explore different on-chip memory designs and a power-gating technique to further reduce the energy consumption, depending upon the utilization across different operations of a CapsuleNet.
RED-Attack: Resource Efficient Decision based Attack for Machine Learning
To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image.
CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Networks (CNNs) in performing tasks like image classification.
Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data.
SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters
In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image.
QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks
Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs).
CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse
In this paper, we propose CapsAcc, the first specialized CMOS-based hardware architecture to perform CapsuleNets inference with high performance and energy efficiency.
Distributed, Parallel, and Cluster Computing Hardware Architecture
TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks
Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase.
MPNA: A Massively-Parallel Neural Array Accelerator with Dataflow Optimization for Convolutional Neural Networks
The state-of-the-art accelerators for Convolutional Neural Networks (CNNs) typically focus on accelerating only the convolutional layers, but do not prioritize the fully-connected layers much.
