Subsessions

• Evaluating Cybersecurity Vulnerabilities in SMPTE ST 2110 Media Networks

  Monday, April 20 | 3 – 3:20 p.m. | N256

  Miles Katz

  This paper presents a threat-lab environment for empirically evaluating cybersecurity risks in SMPTE ST 2110 and AMWA NMOS, based IP media workflows. A segmented testbed, comprising dedicated media, control, and management VLANs; a router VM; and Raspberry Pi nodes acting as sender, receivers, adversary, and monitors, enables controlled execution of representative attack scenarios. These include Layer-2 manipulation (ARP spoofing, MAC flooding), multicast/IGMP disruption (rogue querier, join/report floods), RTP spoofing and payload replacement, and NMOS control-plane interference. Synchronized multi-vantage PCAPs and logs provide temporally aligned measurements of RTP loss, jitter, skew, SSRC behavior, IGMP state transitions, and NMOS heartbeat stability. Across experiments, results consistently show that multicast media playout can appear visually stable even as control-plane signaling and timing degrade. Attacks such as ARP poisoning, IGMP floods, and NMOS HTTP saturation produced significant jitter excursions, registry instability, and forwarding anomalies, yet often with minimal immediate impact on perceived video quality. These findings highlight a critical gap between operational perception and underlying network health. The paper concludes by mapping observed failure modes to practical mitigations and emphasizing the need for robust telemetry and defense-in-depth designs as ST 2110 facilities scale.

• JPEG XS as the Mezzanine Format for Mixed File and IP-Based Production Workflows

  Monday, April 20 | 3:20 – 3:40 p.m. | N256

  Jean-Baptiste Lorent

  In recent years, the boundaries between live- and post-production have blurred. Many shows combine live capture with pre-recorded cinematic segments (e.g., the Paris Olympics). Broadcasters now publish short clips online in real time during events catering to social media audiences. Many sporting events (e.g., F1) are not only aired live, but footage is later repurposed in scripted television documentaries. Modern media workflows therefore integrate file-based production at every stage—before, during, and after events.Maintaining visual consistency between live and pre-recorded content is challenging. Cinema camera-based content offers shallow depth of field (for a more filmic aesthetic), high dynamic range (for richer images), and RAW recording (for flexible & consistent editing). These features are typically absent from broadcast cameras. This explains the growing interest in cinema cameras for live production workflows. To enable these hybrid file- and IP-based workflows, cinema camera manufacturers are now offering native streaming capabilities. Yet, each workflow remains distinct from its application. Mezzanine files transmitted over IP (for remote storage) use proprietary protocols distinct from the ST 2110 / ST 2022 protocols used for live production. Multiple transmission paths (file & live) thus coexist. JPEG XS is uniquely positioned to take this workflow integration further. It already has a proven track-record in broadcast cameras, being supported and widely adopted in ST 2110 (TR-08) and ST 2022 (TR-07). Furthermore, JPEG XS is highly suited for storage as a mezzanine format (high image fidelity, proxy decoding, multi-encoding robustness, software efficiency), particularly compared to existing CODECs.As a result, several cinema camera manufacturers have been supporting or have announced upcoming support for JPEG XS, both as a streaming transport and storage medium. JPEG XS feeds can easily be stored as MXF & IMF by directly extracting JPEG XS payloads from live feeds (TR-07/TR-08), without needing any decompression.This paper and presentation provide an overview of how JPEG XS takes this integration of file- and IP-based workflows further. It also offers a status update of all the supporting specifications and standards that use JPEG XS. Finally, it provides insight into the plans to further improve and leverage JPEG XS in various file repository platforms based on specifications like MXF and IMF.

• Performance Optimization of SMPTE 2110 Applications on COTS Hardware, with Network & JPEG XS Offloading to DPUs

  Monday, April 20 | 3:40 – 4 p.m. | N256

  Ben Runyan, Gauthier Thieren, Thomas True

  As media workflows migrate to software-defined frameworks running on common-off-the-shelf (COTS) hardware, with network-based media essence data exchange, applications executing in this environment can suffer performance and compliance issues due to CPU and/or GPU overloading. In such cases, applications can benefit from more manageable host resources usage by offloading operations to dedicated Data Processing Units (DPUs) and smart Network Interface Cards (NICs). Dedicated DPUs and smart NICs implement the complete network stack in dedicated hardware and utilize kernel bypass to perform network communication without impacting host system operations. DPUs contain additional general purpose processing cores that can be utilized for various types of network stream processing such as encryption or media essence transcoding – one example being JPEG XS. In Broadcast, an example of offloading is to implement the SMPTE ST 2110 stack on the DPUs. The DPUs can reasonably support one video stream: uncompressed streams have significant data rates and thus put significant loads on the DPU cores and memory bandwidth. On the other hand, compressed JPEG XS streams lower the data rates, and thus reduce the overall load on the DPU. This enables a higher stream density, with no compromise on latency, image quality, and lowers power consumption compared to uncompressed video. Thus, JPEG XS in SMPTE 2110 (ST 2110-22) is fully designed to replace uncompressed video at ~10% of the bandwidth. It is a very platform flexible CODEC that can be implemented in hardware or as lightweight parallelizable software. The migration of network transmit and receive operations as well as the JPEG XS transcoding operations to a DPU introduces a reduction in the host CPU usage, freeing more cycles for application functions. Direct Memory Access (DMA) transfers between the DPU and GPU eliminate PCIE bus transactions to and from the host memory that can introduce system jitter. While JPEG XS processing could be performed on the GPU to offload the CPU, moving it to the DPU cores leaves 100% of the GPU processing capabilities for media and AI functions. Moreover, the introduction of JPEG XS transcoding reduces the network bandwidth, allowing for more efficient network usage. This paper will compare the tradeoffs and system performance impacts of using DPUs for media transcode and network functions. It will then demonstrate results for real-world industry use cases in media production.