Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs

The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix multiplication schemes as a means of reducing this burden while maintaining model accuracy requirements. We demonstrate that sparsity can be exploited in arbitrary matrix multiplication, providing runtime benefits compared to a baseline naive algorithm at all sparsity levels. This is a notable departure from the plaintext domain, where there is a trade-off between sparsity and the overhead of the sparse multiplication algorithm. In addition, we propose three sparse multiplication schemes in FHE based on common plaintext sparse encodings. We demonstrate the performance gain is scheme-invariant; however, some sparse schemes vastly reduce the memory storage requirements of the encrypted matrix at high sparsity values. Our proposed sparse schemes yield an average performance gain of 2.5x at 50% unstructured sparsity, with our multi-threading scheme providing a 32.5x performance increase over the equivalent single-threaded sparse computation when utilizing 64 cores.

Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks

Reducing the memory footprint of Machine Learning (ML) models, especially Deep Neural Networks (DNNs), is imperative to facilitate their deployment on resource-constrained edge devices. However, a notable drawback of DNN models lies in their susceptibility to adversarial attacks, wherein minor input perturbations can deceive them. A primary challenge revolves around the development of accurate, resilient, and compact DNN models suitable for deployment on resource-constrained edge devices. This paper presents the outcomes of a compact DNN model that exhibits resilience against both black-box and white-box adversarial attacks. This work has achieved this resilience through training with the QKeras quantization-aware training framework. The study explores the potential of QKeras and an adversarial robustness technique, Jacobian Regularization (JR), to co-optimize the DNN architecture through per-layer JR methodology. As a result, this paper has devised a DNN model employing this co-optimization strategy based on Stochastic Ternary Quantization (STQ). Its performance was compared against existing DNN models in the face of various white-box and black-box attacks. The experimental findings revealed that, the proposed DNN model had small footprint and on average, it exhibited better performance than Quanos and DS-CNN MLCommons/TinyML (MLC/T) benchmarks when challenged with white-box and black-box attacks, respectively, on the CIFAR-10 image and Google Speech Commands audio datasets.

Biases in Edge Language Models: Detection, Analysis, and Mitigation

The integration of large language models (LLMs) on low-power edge devices such as Raspberry Pi, known as edge language models (ELMs), has introduced opportunities for more personalized, secure, and low-latency language intelligence that is accessible to all. However, the resource constraints inherent in edge devices and the lack of robust ethical safeguards in language models raise significant concerns about fairness, accountability, and transparency in model output generation. This paper conducts a comparative analysis of text-based bias across language model deployments on edge, cloud, and desktop environments, aiming to evaluate how deployment settings influence model fairness. Specifically, we examined an optimized Llama-2 model running on a Raspberry Pi 4; GPT 4o-mini, Gemini-1.5-flash, and Grok-beta models running on cloud servers; and Gemma2 and Mistral models running on a MacOS desktop machine. Our results demonstrate that Llama-2 running on Raspberry Pi 4 is 43.23% and 21.89% more prone to showing bias over time compared to models running on the desktop and cloud-based environments. We also propose the implementation of a feedback loop, a mechanism that iteratively adjusts model behavior based on previous outputs, where predefined constraint weights are applied layer-by-layer during inference, allowing the model to correct bias patterns, resulting in 79.28% reduction in model bias.

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations

Quantization of Deep Neural Network (DNN) activations is a commonly used technique to reduce compute and memory demands during DNN inference, which can be particularly beneficial on resource-constrained devices. To achieve high accuracy, existing methods for quantizing activations rely on complex mathematical computations or perform extensive searches for the best hyper-parameters. However, these expensive operations are impractical on devices with limited computation capabilities, memory capacities, and energy budgets. Furthermore, many existing methods do not focus on sub-6-bit (or deep) quantization. To fill these gaps, in this paper we propose DQA (Deep Quantization of DNN Activations), a new method that focuses on sub-6-bit quantization of activations and leverages simple shifting-based operations and Huffman coding to be efficient and achieve high accuracy. We evaluate DQA with 3, 4, and 5-bit quantization levels and three different DNN models for two different tasks, image classification and image segmentation, on two different datasets. DQA shows significantly better accuracy (up to 29.28%) compared to the direct quantization method and the state-of-the-art NoisyQuant for sub-6-bit quantization.

Accelerating PoT Quantization on Edge Devices

Non-uniform quantization, such as power-of-two (PoT) quantization, matches data distributions better than uniform quantization, which reduces the quantization error of Deep Neural Networks (DNNs). PoT quantization also allows bit-shift operations to replace multiplications, but there are limited studies on the efficiency of shift-based accelerators for PoT quantization. Furthermore, existing pipelines for accelerating PoT-quantized DNNs on edge devices are not open-source. In this paper, we first design shift-based processing elements (shift-PE) for different PoT quantization methods and evaluate their efficiency using synthetic benchmarks. Then we design a shift-based accelerator using our most efficient shift-PE and propose PoTAcc, an open-source pipeline for end-to-end acceleration of PoT-quantized DNNs on resource-constrained edge devices. Using PoTAcc, we evaluate the performance of our shift-based accelerator across three DNNs. On average, it achieves a 1.23x speedup and 1.24x energy reduction compared to a multiplier-based accelerator, and a 2.46x speedup and 1.83x energy reduction compared to CPU-only execution. Our code is available at https://github.com/gicLAB/PoTAcc

Designing Efficient LLM Accelerators for Edge Devices

The increase in open-source availability of Large Language Models (LLMs) has enabled users to deploy them on more and more resource-constrained edge devices to reduce reliance on network connections and provide more privacy. However, the high computation and memory demands of LLMs make their execution on resource-constrained edge devices challenging and inefficient. To address this issue, designing new and efficient edge accelerators for LLM inference is crucial. FPGA-based accelerators are ideal for LLM acceleration due to their reconfigurability, as they enable model-specific optimizations and higher performance per watt. However, creating and integrating FPGA-based accelerators for LLMs (particularly on edge devices) has proven challenging, mainly due to the limited hardware design flows for LLMs in existing FPGA platforms. To tackle this issue, in this paper we first propose a new design platform, named SECDA-LLM, that utilizes the SECDA methodology to streamline the process of designing, integrating, and deploying efficient FPGA-based LLM accelerators for the llama.cpp inference framework. We then demonstrate, through a case study, the potential benefits of SECDA-LLM by creating a new MatMul accelerator that supports block floating point quantized operations for LLMs. Our initial accelerator design, deployed on the PYNQ-Z1 board, reduces latency 1.7 seconds per token or ~2 seconds per word) by 11x over the dual-core Arm NEON-based CPU execution for the TinyLlama model.

Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions

Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion process may be riddled with bugs, making the converted models either undeployable or problematic, considerably degrading their prediction correctness. We propose an automated approach for fault localization and repair, Fix-Con, during model conversion between deep learning frameworks. Fix-Con is capable of detecting and fixing faults introduced in model input, parameters, hyperparameters, and the model graph during conversion. Fix-Con uses a set of fault types mined from surveying conversion issues raised to localize potential conversion faults in the converted target model, and then repairs them appropriately, e.g. replacing the parameters of the target model with those from the source model. This is done iteratively for every image in the dataset with output label differences between the source model and the converted target model until all differences are resolved. We evaluate the effectiveness of Fix-Con in fixing model conversion bugs of three widely used image recognition models converted across four different deep learning frameworks. Overall, Fix-Con was able to either completely repair, or significantly improve the performance of 14 out of the 15 erroneous conversion cases.

DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack

Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices. Since such devices are where many emerging deep learning applications lie (e.g., drones, vision-based medical technology), significant bodies of work from both the machine learning and systems communities have attempted to provide optimizations to accelerate DNNs. To help unify these two perspectives, in this paper we combine machine learning and systems techniques within the Deep Learning Acceleration Stack (DLAS), and demonstrate how these layers can be tightly dependent on each other with an across-stack perturbation study. We evaluate the impact on accuracy and inference time when varying different parameters of DLAS across two datasets, seven popular DNN architectures, four DNN compression techniques, three algorithmic primitives with sparse and dense variants, untuned and auto-scheduled code generation, and four hardware platforms. Our evaluation highlights how perturbations across DLAS parameters can cause significant variation and across-stack interactions. The highest level observation from our evaluation is that the model size, accuracy, and inference time are not guaranteed to be correlated. Overall we make 13 key observations, including that speedups provided by compression techniques are very hardware dependent, and that compiler auto-tuning can significantly alter what the best algorithm to use for a given configuration is. With DLAS, we aim to provide a reference framework to aid machine learning and systems practitioners in reasoning about the context in which their respective DNN acceleration solutions exist in. With our evaluation strongly motivating the need for co-design, we believe that DLAS can be a valuable concept for exploring the next generation of co-designed accelerated deep learning solutions.

MutateNN: Mutation Testing of Image Recognition Models Deployed on Hardware Accelerators

With the research advancement of Artificial Intelligence in the last years, there are new opportunities to mitigate real-world problems and advance technologically. Image recognition models in particular, are assigned with perception tasks to mitigate complex real-world challenges and lead to new solutions. Furthermore, the computational complexity and demand for resources of such models has also increased. To mitigate this, model optimization and hardware acceleration has come into play, but effectively integrating such concepts is a challenging and error-prone process. In order to allow developers and researchers to explore the robustness of deep learning image recognition models deployed on different hardware acceleration devices, we propose MutateNN, a tool that provides mutation testing and analysis capabilities for that purpose. To showcase its capabilities, we utilized 21 mutations for 7 widely-known pre-trained deep neural network models. We deployed our mutants on 4 different devices of varying computational capabilities and observed discrepancies in mutants related to conditional operations, as well as some unstable behaviour with those related to arithmetic types.

Fault Localization for Framework Conversions of Image Recognition Models

When deploying Deep Neural Networks (DNNs), developers often convert models from one deep learning framework to another (e.g., TensorFlow to PyTorch). However, this process is error-prone and can impact target model accuracy. To identify the extent of such impact, we perform and briefly present a differential analysis against three DNNs used for image recognition (MobileNetV2, ResNet101, and InceptionV3), converted across four well-known deep learning frameworks (PyTorch, Keras, TensorFlow (TF), and TFLite), which revealed numerous model crashes and output label discrepancies of up to 100%. To mitigate such errors, we present a novel approach towards fault localization and repair of buggy deep learning framework conversions, focusing on pre-trained image recognition models. Our technique consists of four primary stages of analysis: 1) conversion tools, 2) model parameters, 3) model hyperparameters, and 4) graph representation. In addition, we propose a number of strategies towards fault repair of the faults detected. We implement our technique on top of Apache TVM deep learning compiler, and we test it by conducting a preliminary fault localization analysis for the conversion of InceptionV3, from TF to TFLite. Our approach detected that the tf2onnx tool used in the conversion process introduced precision errors to model weights for convolutional layers in particular, which negatively affected the model accuracy. We then repaired the target model by replacing the affected weights with those from source model.