The Threat of Offensive AI to Organizations

Mirsky, Yisroel; Demontis, Ambra; Kotak, Jaidip; Shankar, Ram; Deng, Gelei; Yang, Liu; Zhang, Xiangyu; Lee, Wenke; Elovici, Yuval; Biggio, Battista

doi:10.48550/arxiv.2106.15764

Cited by 1 publication

(1 citation statement)

References 160 publications

(207 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These approaches, however, were also unsuccessful in preventing AI-assisted attacks using DNNs [37,47]. Researchers have now been forced to upgrade the security threat models to incorporate AI-based attacks [33,34]. Because of a massive increase in AI-assisted cyber-attacks on cloud and datacenters, corporations and governments have realized that the best way of defeating offensive AI attacks is by incorporating AI-based defensive strategies.…”

Section: Introductionmentioning

confidence: 99%

Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks

Qureshi¹,

Munir²

2021

Preprint

View full text Add to dashboard Cite

Sparse convolutional neural networks (CNNs) have gained significant traction over the past few years as sparse CNNs can drastically decrease the model size and computations, if exploited befittingly, as compared to their dense counterparts. Sparse CNNs often introduce variations in the layer shapes and sizes, which can prevent dense accelerators from performing well on sparse CNN models. Recently proposed sparse accelerators like SCNN, Eyeriss v2, and SparTen, actively exploit the two-sided or full sparsity, that is, sparsity in both weights and activations, for performance gains. These accelerators, however, either have inefficient micro-architecture (Eyeriss v2, SCNN), which limits their performance, have no support for non-unit stride convolutions (SCNN) and fully-connected (FC) layers (SCNN, SparTen), or suffer massively from systematic load imbalance (SCNN, Eyeriss v2). To circumvent these issues and support both sparse and dense models, we propose Phantom, a multi-threaded, dynamic, and flexible neural computational core. Phantom uses sparse binary mask representation to actively lookahead into sparse computations, and dynamically schedule its computational threads to maximize the thread utilization and throughput. We also generate a two-dimensional (2D) mesh architecture of Phantom neural computational cores, which we refer to as Phantom-2D accelerator, and propose a novel dataflow that supports all layers of a CNN, including unit and non-unit stride convolutions, and FC layers. In addition, Phantom-2D uses a two-level load balancing strategy to minimize the computational idling, thereby, further improving the hardware utilization. To show support for different types of layers, we evaluate the performance of the Phantom architecture on VGG16 and MobileNet. Our simulations show that the Phantom-2D accelerator attains a performance gain of 12×, 4.1×, 1.98×, and 2.36×, over dense architectures, SCNN, SparTen, and Eyeriss v2, respectively. CCS Concepts: • Computer systems organization → Neural networks; Data flow architectures.

show abstract

Section: Introductionmentioning

confidence: 99%