English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In heterogeneous SoCs, accelerators like integrated GPUs (iGPUs) areintegrated on the same chip as CPUs, sharing the memory subsystem. In suchsystems, the massive memory requests from throughput-oriented acceleratorssignificantly interfere with CPU memory requests. In addition to the largeperformance impact, this interference provides an attacker with a strongleakage vector for covert attacks across the processors, which is hard toachieve across the cores in a multi-core CPU. In this paper, we demonstratethat parallel memory write requests of the iGPU and more specifically, themanagement policy of the write buffer in the memory controller (MC) can lead tosignificantly stalling CPU memory read requests in heterogeneous SoCs. Wecharacterize the slowdown on the shared read and write buffers in the memorycontroller and exploit it to build a cross-processor covert channel inIntel-based integrated CPU-GPU systems. We develop two attack variants thatachieve a bandwidth of 1.65 kbps and 4.41 kbps and error rates of 0.49% and4.32% respectively.

Exploiting Parallel Memory Write Requests for Covert Channel Attacks in Integrated CPU-GPU Systems