Sponge examples are test-time inputs optimized to increase energy consumption and prediction latency of deep networks deployed on hardware accelerators. By increasing the fraction of neurons activated during classification, these attacks reduce sparsity in network activation patterns, worsening the performance of hardware accelerators. In this work, we present a novel training-time attack, named sponge poisoning, which aims to worsen energy consumption and prediction latency of neural networks on any test input without affecting classification accuracy. To stage this attack, we assume that the attacker can control only a few model updates during training -- a likely scenario, e.g., when model training is outsourced to an untrusted third party or distributed via federated learning. Our extensive experiments on image classification tasks show that sponge poisoning is effective, and that fine-tuning poisoned models to repair them poses prohibitive costs for most users, highlighting that tackling sponge poisoning remains an open issue.
The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
Radboud University（拉德堡德大学）；Rabobank（拉德堡德银行）；Delft University of Technology（代尔夫特理工大学）；National Technical University of Athens（希腊国家技术大学）；University of Zagreb（扎格列布大学）；University of Bergen（卑尔根大学）
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
School of Computing, Southern Illinois University Carbondale, IL, USA（计算机学院，南方伊利诺伊大学卡本达莱分校）；College of Engineering and Computer Science, Jazan University, Saudi Arabia（工程与计算机科学学院，贾赞大学）；School of Electrical, Computer & Biomedical Engineering, Southern Illinois University Carbondale, IL, USA（电气、计算机与生物医学工程学院，南方伊利诺伊大学卡本达莱分校）
本文首次系统研究针对感知 AI 的能量-延迟 sponge 攻击，并以可穿戴感知为例验证其危害，同时提出用模型剪枝增强防御韧性并量化效率与安全权衡。
An Efficient and Reliable Asynchronous Federated Learning Scheme for Smart Public Transportation
Deakin University（迪肯大学）；Commonwealth Scientific and Industrial Research Organization（澳大利亚联邦科学与工业研究组织）；Xidian University（西安电子科技大学）；Qilu University of Technology（齐鲁工业大学）；Shandong Computer Science Center（山东省计算中心）
A Streamlit-based Artificial Intelligence Trust Platform for Next-Generation Wireless Networks
Old Dominion University（奥多明尼昂大学）；University of Stavanger（斯塔万格大学）；Virginia Commonwealth University（弗吉尼亚联邦大学）；Norwegian University of Science and Technology（挪威科技大学）；eKare, Inc.（eKare公司）
随着人工智能（AI）方法在下一代网络（NextG）中的快速发展和集成，AI算法在频谱使用、带宽、延迟和安全性方面为NextG提供了显著优势。NextG的一个关键特征是AI的集成，即，基于自监督算法的自学习架构，以提高网络的性能。一个安全的人工智能驱动的结构也有望保护NextG网络免受网络攻击。然而，AI本身可能会受到攻击，即，模型中毒是攻击者的目标，它会导致网络安全违规。本文提出了一个使用Streamlit for NextG网络的AI信任平台，允许研究人员评估，防御，认证和验证他们的AI模型和应用程序，以抵御规避，中毒，提取和干扰等对抗性威胁。
Rethinking Software-Defined Networking Link Discovery with Dynamic Randomization
University of Texas at Dallas（德克萨斯大学达拉斯分校）；IBM Research（IBM 研究院）；Georgetown University（乔治城大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；University of California, Riverside（加利福尼亚大学河滨分校）
