Vincent Lannurien
d822cdaa6a
All checks were successful
Build and deploy static pages / build-and-push (push) Successful in 19s
113 lines
5.5 KiB
Markdown
113 lines
5.5 KiB
Markdown
---
|
|
title: IC 2025 Digest
|
|
venue: IC
|
|
year: 2025
|
|
date: '2025-01-01'
|
|
tags: []
|
|
paper_count: 10
|
|
draft: false
|
|
---
|
|
|
|
10 papers selected.
|
|
|
|
---
|
|
|
|
### Rethinking Computing Systems in the Era of Climate Crisis: A Call for a Sustainable Computing Continuum
|
|
|
|
*Ella Peltonen, Suzan Bayhan, David Bermbach, Sebastian Buschjäger *et al.**
|
|
|
|
**TL;DR** — A multi-author position paper calling for carbon-aware design principles across the cloud-to-edge computing continuum, surveying energy measurement, workload scheduling, and hardware lifecycle challenges.
|
|
|
|
**Why notable** — Establishes a community research agenda for sustainable computing infrastructure at a time when datacenter and edge energy consumption is under increasing regulatory and societal scrutiny.
|
|
|
|
---
|
|
|
|
### Toward Carbon-Aware Data Transfers
|
|
|
|
*Jacob Goldverg, Hasibul Jamil, Elvis Rodrigues, Tevfik Kosar*
|
|
|
|
**TL;DR** — Proposes scheduling and routing strategies for large-scale data transfers that minimize carbon emissions by leveraging time- and location-varying grid carbon intensity signals.
|
|
|
|
**Why notable** — Delivers a practical, implementable mechanism for reducing the carbon footprint of Internet data movement, directly applicable to data-intensive scientific and cloud workflows.
|
|
|
|
---
|
|
|
|
### Zero Trust-Driven Collaborative Intrusion Detection in Internet of Things: A Continuous Trust Assessment Approach
|
|
|
|
*Xinxin Wang, Qingjun Yuan, Yongjuan Wang, Jihong Teng *et al.**
|
|
|
|
**TL;DR** — Designs a collaborative intrusion detection system for IoT networks grounded in zero-trust principles, continuously reassessing device trust scores to isolate compromised nodes in real time.
|
|
|
|
**Why notable** — Demonstrates how zero-trust architectures can be operationalized at IoT scale, providing a concrete detection model with empirical evaluation on real traffic.
|
|
|
|
---
|
|
|
|
### Securing Voice Authentication Applications Against Targeted Data Poisoning
|
|
|
|
*Alireza Mohammadi, Keshav Sood, Asef Nazari, Dhananjay R. Thiruvady*
|
|
|
|
**TL;DR** — Identifies and mitigates targeted data poisoning attacks on voice authentication systems by detecting and filtering malicious training samples before model updates are applied.
|
|
|
|
**Why notable** — Highlights a practical and underexplored attack surface in biometric authentication services, with defenses validated against realistic adversarial scenarios.
|
|
|
|
---
|
|
|
|
### Characterization of Probabilistic Structure of Internet Traffic During COVID-19: A Study Based on MAWI Data
|
|
|
|
*Anoushka Mittal, Pranav Jain, Karmeshu, Shachi Sharma*
|
|
|
|
**TL;DR** — Applies statistical modeling to MAWI backbone traffic traces collected during COVID-19 to characterize shifts in Internet traffic distributions and identify new usage patterns.
|
|
|
|
**Why notable** — Provides rare longitudinal empirical evidence of how a major societal disruption altered Internet traffic structure, with implications for capacity planning and anomaly detection baselines.
|
|
|
|
---
|
|
|
|
### iGenEdge: Intelligent Generative AI Service Deployment for Edge-Connected IoT Devices
|
|
|
|
*Faiza Akram, Asad Waqar Malik, Samee U. Khan*
|
|
|
|
**TL;DR** — Proposes iGenEdge, a framework that intelligently partitions and deploys generative AI inference tasks across edge servers and IoT devices based on latency, energy, and model accuracy constraints.
|
|
|
|
**Why notable** — Addresses the critical engineering challenge of running large generative models close to IoT data sources, with practical placement algorithms and experimental validation.
|
|
|
|
---
|
|
|
|
### Smaller, Smarter, Closer: The Edge of Collaborative Generative Artificial Intelligence
|
|
|
|
*Roberto Morabito, SiYoung Jang*
|
|
|
|
**TL;DR** — Surveys strategies for deploying collaborative generative AI models at the network edge, covering model compression, offloading, and inter-device coordination techniques.
|
|
|
|
**Why notable** — Gives a clear-eyed assessment of where edge generative AI stands today and what infrastructure advances are needed, serving as a practical guide for edge platform designers.
|
|
|
|
---
|
|
|
|
### Memory-Augmented Autoencoder with Reservoir Computing for Edge-Based Anomaly Detection in Autonomous Systems
|
|
|
|
*Fabiha Nowshin, Zheng Dong 0002, Yang Yi 0002*
|
|
|
|
**TL;DR** — Combines a memory-augmented autoencoder with reservoir computing to detect anomalies in autonomous system sensor streams directly on resource-constrained edge hardware.
|
|
|
|
**Why notable** — Demonstrates strong anomaly detection accuracy under tight edge compute budgets, making it directly relevant to safety-critical IoT and autonomous vehicle deployments.
|
|
|
|
---
|
|
|
|
### Ship-to-Shore Network Monitoring: The Research Vessel Sikuliaq Experience
|
|
|
|
*Komal Thareja, Anirban Mandal, Julian Race, Paul Ruth *et al.**
|
|
|
|
**TL;DR** — Presents a real-world case study of continuous network monitoring for a research vessel operating over satellite links, characterizing link quality, disruptions, and measurement methodology.
|
|
|
|
**Why notable** — Offers rare empirical data on challenged maritime Internet connectivity, informing the design of resilient monitoring and science workflows for remote and mobile environments.
|
|
|
|
---
|
|
|
|
### Think Locally, Act Globally: A Programming Model for Decentralized Applications
|
|
|
|
*Julian Haas, Christian Kuessner, Ragnar Mogk, Mira Mezini*
|
|
|
|
**TL;DR** — Introduces a programming model that lets developers write local per-node logic while the runtime automatically enforces global consistency and coordination across a decentralized application.
|
|
|
|
**Why notable** — Tackles the fundamental complexity of building correct decentralized Internet applications, offering a principled abstraction that could reduce the gap between distributed systems theory and practice.
|
|
|