Saurabh Bagchi
YOU?
Author Swipe
View article: MAUI: Reconstructing Private Client Data in Federated Transfer Learning
MAUI: Reconstructing Private Client Data in Federated Transfer Learning Open
Recent works in federated learning (FL) have shown the utility of leveraging transfer learning for balancing the benefits of FL and centralized learning. In this setting, federated training happens after a stable point has been reached thr…
View article: Are Fast Methods Stable in Adversarially Robust Transfer Learning?
Are Fast Methods Stable in Adversarially Robust Transfer Learning? Open
Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…
View article: Ascendra: Dynamic Request Prioritization for Efficient LLM Serving
Ascendra: Dynamic Request Prioritization for Efficient LLM Serving Open
The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly…
View article: The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape Open
Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal dev…
View article: Learning to Inference Adaptively for Multimodal Large Language Models
Learning to Inference Adaptively for Multimodal Large Language Models Open
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent effort on improving t…
View article: Evaluation-free Time-series Forecasting Model Selection via Meta-learning
Evaluation-free Time-series Forecasting Model Selection via Meta-learning Open
Time-series forecasting models are invariably used in a variety of domains for crucial decision-making. Traditionally these models are constructed by experts with considerable manual effort. Unfortunately, this approach has poor scalabilit…
View article: HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices
HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices Open
Multi-Object Tracking (MOT) poses significant challenges in computer vision. Despite its wide application in robotics, autonomous driving, and smart manufacturing, there is limited literature addressing the specific challenges of running M…
View article: Dynamic DAG-Application Scheduling for Multi-Tier Edge Computing in Heterogeneous Networks
Dynamic DAG-Application Scheduling for Multi-Tier Edge Computing in Heterogeneous Networks Open
Edge computing is deemed a promising technique to execute latency-sensitive applications by offloading computation-intensive tasks to edge servers. Extensive research has been conducted in the field of end-device to edge server task offloa…
View article: The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape Open
Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal dev…
View article: Delphi: Efficient Asynchronous Approximate Agreement for Distributed Oracles
Delphi: Efficient Asynchronous Approximate Agreement for Distributed Oracles Open
Agreement protocols are crucial in various emerging applications, spanning from distributed (blockchains) oracles to fault-tolerant cyber-physical systems. In scenarios where sensor/oracle nodes measure a common source, maintaining output …
View article: Adversarial Attacks on Reinforcement Learning Agents for Command and Control
Adversarial Attacks on Reinforcement Learning Agents for Command and Control Open
Given the recent impact of Deep Reinforcement Learning in training agents to win complex games like StarCraft and DoTA(Defense Of The Ancients) - there has been a surge in research for exploiting learning based techniques for professional …
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: IEEE Computer Society
IEEE Computer Society Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning
Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning Open
Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client …
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: EESMR
EESMR Open
Modern Byzantine Fault-Tolerant State Machine Replication (BFT-SMR) solutions focus on reducing communication complexity, improving throughput, or lowering latency. This work explores the energy efficiency of BFT-SMR protocols. First, we p…
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: Game Theory in Distributed Systems Security: Foundations, Challenges, and Future Directions
Game Theory in Distributed Systems Security: Foundations, Challenges, and Future Directions Open
Many of our critical infrastructure systems and personal computing systems have a distributed computing systems structure. The incentives to attack them have been growing rapidly as has their attack surface due to increasing levels of conn…
View article: IEEE Computer Society Information
IEEE Computer Society Information Open
Engaging professionals from all areas of computing, the IEEE Computer Society sets the standard for education and engagement that fuels global technological advancement.Through conferences, publications, and programs, IEEE CS empowers, gui…
View article: Benchmarking Algorithms for Federated Domain Generalization
Benchmarking Algorithms for Federated Domain Generalization Open
While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based heterogeneity in clie…
View article: FLAIR: Defense against Model Poisoning Attack in Federated Learning
FLAIR: Defense against Model Poisoning Attack in Federated Learning Open
Federated learning—multi-party, distributed learning in a decentralized environment—is vulnerable to model poisoning attacks, more so than centralized learning. This is because malicious clients can collude and send in carefully tailored m…
View article: Security Properties of Virtual Remotes and SPOOKing their violations
Security Properties of Virtual Remotes and SPOOKing their violations Open
As Smart TV devices become more prevalent in our lives, it becomes increasingly important to evaluate the security of these devices. In addition to a smart and connected ecosystem through apps, Smart TV devices expose a WiFi remote protoco…