Tootfinder

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Xiaoxing Mo, Yuxuan Cheng, Nan Sun, Leo Yu Zhang, Wei Luo, Shang Gao
https://arxiv.org/abs/2506.10722

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics (TED) has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be vulnerable to backdoor attacks that adaptively distort topological representation distributions across network layers. To address this limitation, we propose TED-LaST (Topological Evolution Dynamics agai…

Multi-Level Damage-Aware Graph Learning for Resilient UAV Swarm Networks
Huan Lin, Chenguang Zhu, Lianghui Ding, Feng Yang
https://arxiv.org/abs/2506.09703

Multi-Level Damage-Aware Graph Learning for Resilient UAV Swarm Networks
Unmanned aerial vehicle (UAV) swarm networks leverage resilient algorithms to address communication network split issues and restore connectivity. However, existing graph learning-based resilient algorithms face over-aggregation and non-convergence problems caused by uneven and sparse topology under massive damage scenarios. To alleviate these problems, we propose a novel Multi-Level Damage-Aware Graph Learning (ML-DAGL) algorithm, which generates recovery trajectories by mining information fro…

Data-driven Identification of Attractors Using Machine Learning
Marcio Gameiro, Brittany Gelb, William Kalies, Miroslav Kramar, Konstantin Mischaikow, Paul Tatasciore
https://arxiv.org/abs/2506.06492

Data-driven Identification of Attractors Using Machine Learning
In this paper we explore challenges in developing a topological framework in which machine learning can be used to robustly characterize global dynamics. Specifically, we focus on learning a useful discretization of the phase space of a flow on compact, hyperrectangle in $\mathbb{R}^n$ from a neural network trained on labeled orbit data. A characterization of the structure of the global dynamics is obtained from approximations of attracting neighborhoods provided by the phase space discretizati…

Fully-Distributed Construction of Byzantine-Resilient Dynamic Peer-to-Peer Networks
Aayush Gupta, Gopal Pandurangan
https://arxiv.org/abs/2506.04368 https:…

Fully-Distributed Construction of Byzantine-Resilient Dynamic Peer-to-Peer Networks
We address a fundamental problem in Peer-to-Peer (P2P) networks, namely, constructing and maintaining dynamic P2P overlay network topologies with essential properties such as connectivity, low diameter, and high expansion, that are resilient to continuous high churn and the presence of a large number of malicious (Byzantine) nodes. Our main goal is to construct and maintain a sparse (bounded degree) expander topology despite high churn and a large number of Byzantine nodes. Such an expander top…

This https://arxiv.org/abs/2308.02636 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Learning from Topology: Cosmological Parameter Estimation from the Large-scale Structure
The topology of the large-scale structure of the universe contains valuable information on the underlying cosmological parameters. While persistent homology can extract this topological information, the optimal method for parameter estimation from the tool remains an open question. To address this, we propose a neural network model to map persistence images to cosmological parameters. Through a parameter recovery test, we demonstrate that our model makes accurate and precise estimates, consider…

INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization
Aleksandr Algazinov, Joydeep Chandra, Matt Laing
https://arxiv.org/abs/2505.24269

INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization
In-network computation represents a transformative approach to addressing the escalating demands of Artificial Intelligence (AI) workloads on network infrastructure. By leveraging the processing capabilities of network devices such as switches, routers, and Network Interface Cards (NICs), this paradigm enables AI computations to be performed directly within the network fabric, significantly reducing latency, enhancing throughput, and optimizing resource utilization. This paper provides a compre…

Minimal Deterministic Echo State Networks Outperform Random Reservoirs in Learning Chaotic Dynamics
Francesco Martinuzzi
https://arxiv.org/abs/2507.06050 h…

Minimal Deterministic Echo State Networks Outperform Random Reservoirs in Learning Chaotic Dynamics
Machine learning (ML) is widely used to model chaotic systems. Among ML approaches, echo state networks (ESNs) have received considerable attention due to their simple construction and fast training. However, ESN performance is highly sensitive to hyperparameter choices and to its random initialization. In this work, we demonstrate that ESNs constructed using deterministic rules and simple topologies (MESNs) outperform standard ESNs in the task of chaotic attractor reconstruction. We use a data…

Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization
Ruilong Wu, Xinjiao Li, Yisu Wang, Xinyu Chen, Dirk Kutscher
https://arxiv.org/abs/2506.02787

Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization
Hybrid parallelism techniques are essential for efficiently training large language models (LLMs). Nevertheless, current automatic parallel planning frameworks often overlook the simultaneous consideration of node heterogeneity and dynamic network topology changes, limiting their effectiveness in practical applications. In this paper, we address these limitations by modeling heterogeneous nodes within dynamically changing network environments and leveraging simulation-based strategies to determ…

Network Structures as an Attack Surface: Topology-Based Privacy Leakage in Federated Learning
Murtaza Rangwala, Richard O. Sinnott, Rajkumar Buyya
https://arxiv.org/abs/2506.19260

Network Structures as an Attack Surface: Topology-Based Privacy Leakage in Federated Learning
Federated learning systems increasingly rely on diverse network topologies to address scalability and organizational constraints. While existing privacy research focuses on gradient-based attacks, the privacy implications of network topology knowledge remain critically understudied. We conduct the first comprehensive analysis of topology-based privacy leakage across realistic adversarial knowledge scenarios, demonstrating that adversaries with varying degrees of structural knowledge can infer s…

Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies
Ximeng Liu, Shizhen Zhao, Xinbing Wang
https://arxiv.org/abs/2506.23640

Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies
Recently, researchers have explored ML-based Traffic Engineering (TE), leveraging neural networks to solve TE problems traditionally addressed by optimization. However, existing ML-based TE schemes remain impractical: they either fail to handle topology changes or suffer from poor scalability due to excessive computational and memory overhead. To overcome these limitations, we propose Geminet, a lightweight and scalable ML-based TE framework that can handle changing topologies. Geminet is built…