arXiv subjects

Guru Venkataramani

Publications and source records attributed to Guru Venkataramani.

At least 19 recordsLinked to original sources

arXiv2026

Emulated Integrity Replica: Enabling Self-Healing on FPGA SoCs via Hierarchical Twins

Convolutional neural networks (CNNs) are increasingly being deployed on system-on-chip (SoC) platforms, where hardware-accelerated inference enables low-latency edge computing. Achieving fault tolerance on these devices remains challenging because conventional redundancy (dual/triple modular redundancy, DMR/TMR) incurs high resource cost, while software-centric methods (e.g., algorithm-based fault tolerance (ABFT), checkpoint-restart, instruction-level duplication, and software watchdogs/assertions) introduce nontrivial latency/energy overheads, reduce model accuracy, or provide inadequate coverage for accelerator-induced faults. In this paper, we propose Emulated Integrity Replica (EIR), a hierarchical digital-twin framework for FPGA SoCs that provides autonomous fault detection and recovery. Unlike DMR/TMR, which replicates hardware logic and incurs proportional area and power overheads, EIR avoids fabric-level duplication by exploiting temporal slack in the processing system (PS). During accelerator execution in the programmable logic (PL), the PS typically remains underutilized; EIR capitalizes on these idle cycles to host two complementary twins: (i) Rabbit: a coarse-grained behavioral model for rapid fault detection and (ii) Tortoise: a fine-grained gate-level model that performs precise recovery from checkpointed states. The accelerator state is captured periodically, leveraging the accelerator's execution-speed profiling to balance performance overhead and resilience. Experiments on representative workloads show that EIR achieves high empirical fault coverage relative to a DMR baseline while reducing energy and area under the evaluated fault model and workload assumptions, indicating a practical path to resilient edge-AI deployments under strict resource budgets.

cs.AR↗

arXiv2024

SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To overcome this, SwiftRL explores Processing-In-Memory (PIM) architectures to accelerate RL workloads. We achieve near-linear performance scaling by implementing RL algorithms like Tabular Q-learning and SARSA on UPMEM PIM systems and optimizing for hardware. Our experiments on OpenAI GYM environments using UPMEM hardware demonstrate superior performance compared to CPU and GPU implementations.

cs.LG↗

arXiv2023

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due to their resource bottlenecks. Recent research efforts have focused on model-heterogeneous FL, by extracting reduced-size models from the global model and applying them to local clients accordingly. Despite the empirical success, general theoretical guarantees of convergence on this method remain an open question. This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time. In particular, we prove that under certain sufficient conditions and for both IID and non-IID data, these algorithms converge to a stationary point of standard FL for general smooth cost functions. Moreover, we introduce the concept of minimum coverage index, together with model reduction noise, which will determine the convergence of heterogeneous federated learning, and therefore we advocate for a holistic approach that considers both factors to enhance the efficiency of heterogeneous federated learning.

cs.LG↗

arXiv2023

Exploiting Partial Common Information Microstructure for Multi-Modal Brain Tumor Segmentation

Learning with multiple modalities is crucial for automated brain tumor segmentation from magnetic resonance imaging data. Explicitly optimizing the common information shared among all modalities (e.g., by maximizing the total correlation) has been shown to achieve better feature representations and thus enhance the segmentation performance. However, existing approaches are oblivious to partial common information shared by subsets of the modalities. In this paper, we show that identifying such partial common information can significantly boost the discriminative power of image segmentation models. In particular, we introduce a novel concept of partial common information mask (PCI-mask) to provide a fine-grained characterization of what partial common information is shared by which subsets of the modalities. By solving a masked correlation maximization and simultaneously learning an optimal PCI-mask, we identify the latent microstructure of partial common information and leverage it in a self-attention module to selectively weight different feature representations in multi-modal data. We implement our proposed framework on the standard U-Net. Our experimental results on the Multi-modal Brain Tumor Segmentation Challenge (BraTS) datasets outperform those of state-of-the-art segmentation baselines, with validation Dice similarity coefficients of 0.920, 0.897, 0.837 for the whole tumor, tumor core, and enhancing tumor on BraTS-2020.

cs.CV↗

arXiv2023

AccMER: Accelerating Multi-Agent Experience Replay with Cache Locality-aware Prioritization

Multi-Agent Experience Replay (MER) is a key component of off-policy reinforcement learning~(RL) algorithms. By remembering and reusing experiences from the past, experience replay significantly improves the stability of RL algorithms and their learning efficiency. In many scenarios, multiple agents interact in a shared environment during online training under centralized training and decentralized execution~(CTDE) paradigm. Current multi-agent reinforcement learning~(MARL) algorithms consider experience replay with uniform sampling or based on priority weights to improve transition data sample efficiency in the sampling phase. However, moving transition data histories for each agent through the processor memory hierarchy is a performance limiter. Also, as the agents' transitions continuously renew every iteration, the finite cache capacity results in increased cache misses. To this end, we propose \name, that repeatedly reuses the transitions~(experiences) for a window of $n$ steps in order to improve the cache locality and minimize the transition data movement, instead of sampling new transitions at each step. Specifically, our optimization uses priority weights to select the transitions so that only high-priority transitions will be reused frequently, thereby improving the cache performance. Our experimental results on the Predator-Prey environment demonstrate the effectiveness of reusing the essential transitions based on the priority weights, where we observe an end-to-end training time reduction of $25.4\%$~(for $32$ agents) compared to existing prioritized MER algorithms without notable degradation in the mean reward.

cs.MA↗

arXiv2023

Towards Efficient Multi-Agent Learning Systems

Multi-Agent Reinforcement Learning (MARL) is an increasingly important research field that can model and control multiple large-scale autonomous systems. Despite its achievements, existing multi-agent learning methods typically involve expensive computations in terms of training time and power arising from large observation-action space and a huge number of training steps. Therefore, a key challenge is understanding and characterizing the computationally intensive functions in several popular classes of MARL algorithms during their training phases. Our preliminary experiments reveal new insights into the key modules of MARL algorithms that limit the adoption of MARL in real-world systems. We explore neighbor sampling strategy to improve cache locality and observe performance improvement ranging from 26.66% (3 agents) to 27.39% (12 agents) during the computationally intensive mini-batch sampling phase. Additionally, we demonstrate that improving the locality leads to an end-to-end training time reduction of 10.2% (for 12 agents) compared to existing multi-agent algorithms without significant degradation in the mean reward.

cs.MA↗

arXiv2023

MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization

Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL algorithms. Many decision-making problems in practice naturally involve multiple agents and require multi-agent reinforcement learning (MARL) under centralized training decentralized execution paradigm. Nevertheless, existing MARL algorithms often adopt standard experience replay where the transitions are uniformly sampled regardless of their importance. Finding prioritized sampling weights that are optimized for MARL experience replay has yet to be explored. To this end, we propose MAC-PO, which formulates optimal prioritized experience replay for multi-agent problems as a regret minimization over the sampling weights of transitions. Such optimization is relaxed and solved using the Lagrangian multiplier approach to obtain the close-form optimal sampling weights. By minimizing the resulting policy regret, we can narrow the gap between the current policy and a nominal optimal policy, thus acquiring an improved prioritization scheme for multi-agent tasks. Our experimental results on Predator-Prey and StarCraft Multi-Agent Challenge environments demonstrate the effectiveness of our method, having a better ability to replay important transitions and outperforming other state-of-the-art baselines.

cs.LG↗

arXiv2023

Scalability Bottlenecks in Multi-Agent Reinforcement Learning Systems

Multi-Agent Reinforcement Learning (MARL) is a promising area of research that can model and control multiple, autonomous decision-making agents. During online training, MARL algorithms involve performance-intensive computations such as exploration and exploitation phases originating from large observation-action space belonging to multiple agents. In this article, we seek to characterize the scalability bottlenecks in several popular classes of MARL algorithms during their training phases. Our experimental results reveal new insights into the key modules of MARL algorithms that limit the scalability, and outline potential strategies that may help address these performance issues.

cs.MA↗

arXiv2022

On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning

One of the biggest challenges in Federated Learning (FL) is that client devices often have drastically different computation and communication resources for local updates. To this end, recent research efforts have focused on training heterogeneous local models obtained by pruning a shared global model. Despite empirical success, theoretical guarantees on convergence remain an open question. In this paper, we present a unifying framework for heterogeneous FL algorithms with {\em arbitrary} adaptive online model pruning and provide a general convergence analysis. In particular, we prove that under certain sufficient conditions and on both IID and non-IID data, these algorithms converges to a stationary point of standard FL for general smooth cost functions, with a convergence rate of $O(\frac{1}{\sqrt{Q}})$. Moreover, we illuminate two key factors impacting convergence: pruning-induced noise and minimum coverage index, advocating a joint design of local pruning masks for efficient training.

cs.LG↗

arXiv2022

A Framework for Server Authentication using Communication Protocol Dialects

In today's world, computer networks have become vulnerable to numerous attacks. In both wireless and wired networks, one of the most common attacks is man-in-the-middle attacks, within which session hijacking, context confusion attacks have been the most attempted. A potential attacker may have enough time to launch an attack targeting these vulnerabilities (such as rerouting the target request to a malicious server or hijacking the traffic). A viable strategy to solve this problem is, by dynamically changing the system properties, configurations and create unique fingerprints to identify the source. However, the existing work of fingerprinting mainly focuses on lower-level properties (e.g IP address), and only these types of properties are restricted for mutation. We develop a novel system, called Verify-Pro, to provide server authentication using communication protocol dialects, that uses a client-server architecture based on network protocols for customizing the communication transactions. For each session, a particular sequence of handshakes will be used as dialects. So, given the context, with the establishment of a one-time username and password, we use the dialects as an authentication mechanism for each request (e.g get filename in FTP) throughout the session, which enforces continuous authentication. Specifically, we leverage a machine learning approach on both client and server machines to trigger a specific dialect that dynamically changes for each request. We implement a prototype of Verify-Pro and evaluate its practicality on standard communication protocols FTP, HTTP & internet of things protocol MQTT. Our experimental results show that by sending misleading information through message packets from an attacker at the application layer, it is possible for the recipient to identify if the sender is genuine or a spoofed one, with a negligible overhead of 0.536%.

cs.CR↗

arXiv2021

Popcorns-Pro: A Cooperative Network-Server Approach for Data Center Energy Optimization

Data centers have become a popular computing platform for various applications, and they account for nearly 2% of total US energy consumption. Therefore, it has become important to optimize data center power, and reduce their energy footprint. Most existing work optimizes power in servers and networks independently and does not address them together in a holistic fashion that has the potential to achieve greater power savings. In this article, we present PopcornsPro, a cooperative server network framework for energy optimization. We present a comprehensive power model for heterogeneous data center switches along with low power mode designs in combination with the server power model. We design job scheduling algorithms that place tasks onto servers in a power-aware manner, such that servers and network switches can take effective advantage of low power state and available network link capacities. Our experimental results show that we are able to achieve significantly higher savings up to 80% compared to the previously well-known server and network power optimization policies.

cs.AR↗

arXiv2021

PT-VTON: an Image-Based Virtual Try-On Network with Progressive Pose Attention Transfer

The virtual try-on system has gained great attention due to its potential to give customers a realistic, personalized product presentation in virtualized settings. In this paper, we present PT-VTON, a novel pose-transfer-based framework for cloth transfer that enables virtual try-on with arbitrary poses. PT-VTON can be applied to the fashion industry within minimal modification of existing systems while satisfying the overall visual fashionability and detailed fabric appearance requirements. It enables efficient clothes transferring between model and user images with arbitrary pose and body shape. We implement a prototype of PT-VTON and demonstrate that our system can match or surpass many other approaches when facing a drastic variation of poses by preserving detailed human and fabric characteristic appearances. PT-VTON is shown to outperform alternative approaches both on machine-based quantitative metrics and qualitative results.

cs.CV↗

arXiv2021

MPD: Moving Target Defense through Communication Protocol Dialects

Communication protocol security is among the most significant challenges of the Internet of Things (IoT) due to the wide variety of hardware and software technologies involved. Moving target defense (MTD) has been adopted as an innovative strategy to solve this problem by dynamically changing target system properties and configurations to obfuscate the attack surface. Nevertheless, the existing work of MTD primarily focuses on lower-level properties (e.g., IP addresses or port numbers), and only a limited number of variations can be generated based on these properties. In this paper, we propose a new approach of MTD through communication protocol dialects (MPD) - which dynamically customizes a communication protocol into various protocol dialects and leverages them to create a moving target defense. Specifically, MPD harnesses a dialect generating function to create protocol dialects and then a mapping function to select one specific dialect for each packet during communication. To keep different network entities in synchronization, we also design a self-synchronization mechanism utilizing a pseudo-random number generator with the input of a pre-shared secret key and previously sent packets. We implement a prototype of MPD and evaluate its feasibility on standard network protocol (i.e., File Transfer Protocol) and internet of things protocol (i.e., Message Queuing Telemetry Transport). The results indicate that MPD can create a moving target defense with protocol dialects to effectively address various attacks - including the denial of service attack and malicious packet modifications - with negligible overhead.

cs.CR↗

arXiv2021

Integrated Reasoning Engine for Pointer-related Code Clone Detection

Detecting similar code fragments, usually referred to as code clones, is an important task. In particular, code clone detection can have significant uses in the context of vulnerability discovery, refactoring and plagiarism detection. However, false positives are inevitable and always require manual reviews. In this paper, we propose Twin-Finder+, a novel closed-loop approach for pointer-related code clone detection that integrates machine learning and symbolic execution techniques to achieve precision. Twin-Finder+ introduces a formal verification mechanism to automate such manual reviews process. Our experimental results show Twin-Finder+ that can remove 91.69% false positives in average. We further conduct security analysis for memory safety using real-world applications, Links version 2.14 and libreOffice-6.0.0.1. Twin-Finder+ is able to find 6 unreported bugs in Links version 2.14 and one public patched bug in libreOffice-6.0.0.1.

cs.SE↗

arXiv2020

Twin-Finder: Integrated Reasoning Engine for Pointer-related Code Clone Detection

Detecting code clones is crucial in various software engineering tasks. In particular, code clone detection can have significant uses in the context of analyzing and fixing bugs in large scale applications. However, prior works, such as machine learning-based clone detection, may cause a considerable amount of false positives. In this paper, we propose Twin-Finder, a novel, closed-loop approach for pointer-related code clone detection that integrates machine learning and symbolic execution techniques to achieve precision. Twin-Finder introduces a clone verification mechanism to formally verify if two clone samples are indeed clones and a feedback loop to automatically generated formal rules to tune machine learning algorithm and further reduce the false positives. Our experimental results show that Twin-Finder can swiftly identify up 9X more code clones comparing to a tree-based clone detector, Deckard and remove an average 91.69% false positives.

cs.SE↗

arXiv2019

HolDCSim: A Holistic Simulator for Data Centers

Cloud computing based systems, that span data centers, are commonly deployed to offer high performance for user service requests. As data centers continue to expand, computer architects and system designers are facing many challenges on how to balance resource utilization efficiency, server and network performance, energy consumption and quality-of-service (QoS) demands from the users. To develop effective data center management policies, it becomes essential to have an in-depth understanding and synergistic control of the various sub-components inside large scale computing systems, that include both computation and communication resources. In this paper, we propose HolDCSim, a light-weight, holistic, extensible, event-driven data center simulation platform that effectively models both server and network architectures. HolDCSim can be used in a variety of data center system studies including job/task scheduling, resource provisioning, global and local server farm power management, and network and server performance analysis. We demonstrate the design of our simulation infrastructure, and illustrate the usefulness of our framework with several case studies that analyze server/network performance and energy efficiency. We also perform validation on real machines to verify our simulator.

cs.DC↗

arXiv2019

CHOP: Bypassing Runtime Bounds Checking Through Convex Hull OPtimization

Unsafe memory accesses in programs written using popular programming languages like C/C++ have been among the leading causes for software vulnerability. Prior memory safety checkers such as SoftBound enforce memory spatial safety by checking if every access to array elements are within the corresponding array bounds. However, it often results in high execution time overhead due to the cost of executing the instructions associated with bounds checking. To mitigate this problem, redundant bounds check elimination techniques are needed. In this paper, we propose CHOP, a Convex Hull OPtimization based framework, for bypassing redundant memory bounds checking via profile-guided inferences. In contrast to existing check elimination techniques that are limited by static code analysis, our solution leverages a model-based inference to identify redundant bounds checking based on runtime data from past program executions. For a given function, it rapidly derives and updates a knowledge base containing sufficient conditions for identifying redundant array bounds checking. We evaluate CHOP on real-world applications and benchmark (such as SPEC) and the experimental results show that on average 80.12% of dynamic bounds check instructions can be avoided, resulting in improved performance up to 95.80% over SoftBound.

cs.PL↗

arXiv2019

Towards a Better Indicator for Cache Timing Channels

Recent studies highlighting the vulnerability of computer architecture to information leakage attacks have been a cause of significant concern. Among the various classes of microarchitectural attacks, cache timing channels are especially worrisome since they have the potential to compromise users' private data at high bit rates. Prior works have demonstrated the use of cache miss patterns to detect these attacks. We find that cache miss traces can be easily spoofed and thus they may not be able to identify smarter adversaries. In this work, we show that \emph{cache occupancy}, which records the number of cache blocks owned by a specific process, can be leveraged as a stronger indicator for the presence of cache timing channels. We observe that the modulation of cache access latency in timing channels can be recognized through analyzing pairwise cache occupancy patterns. Our experimental results show that cache occupancy patterns cannot be easily obfuscated even by advanced adversaries that successfully evade cache miss-based detection.

cs.CR↗