DoubleVerify identifies KickBot CTV fraud scheme targeting premium sports inventory

The discovery of this bot operation highlights a sophisticated shift in ad fraud where scripts are tailored to specific content genres to bypass traditional detection. As live sports become the primary driver for CTV ad spend, the high CPMs associated with these events create a lucrative target for automated falsification. This development forces a change in verification strategies, moving beyond simple device pings to analyzing behavioral context like session duration relative to live event timing. The industry must now account for the unpredictable nature of live programming to protect premium budgets. Watch for increased adoption of AI-driven verification tools as programmatic bidding surges during the upcoming World Series and pro football season.

DoubleVerify operates within an increasingly competitive CTV fraud detection market where verification vendors race to identify sophisticated bot operations before they drain advertiser budgets. In June 2026, the IEEE ComSoc Technology Blog documented a cluster of announcements signaling a shift from isolated AI pilots to production-grade AI operations deployed across live networks, a trend that parallels the ad-tech industry's own move toward AI-driven fraud detection at scale. The same agentic AI architectures being deployed in telecom networks are now being adapted by verification platforms to identify behavioral anomalies in CTV impression data, including session timing patterns that deviate from live event schedules.

The business stakes for CTV fraud detection have intensified as programmatic sports advertising commands premium rates. Nokia announced partnerships with AWS and Databricks to build unified data and cloud control layers for autonomous network operations, claiming automation rates higher than 90 percent and service delivery times of four hours or less. While that announcement targets telecom infrastructure, the underlying architecture of unified data platforms feeding AI agents mirrors the approach verification vendors like DoubleVerify are adopting to correlate impression data across fragmented CTV supply chains. The convergence of real-time analytics and cross-domain AI agents represents the same technical pattern being applied to detect coordinated fraud across multiple ad exchanges simultaneously.

On the technical front, the divergence between competing AI deployment strategies offers instructive parallels for fraud detection. Ericsson and Nokia are diverging on AI-RAN architecture, with Nokia running all Layer 1 functions on Nvidia GPUs while Ericsson limits GPU use to forward error correction, illustrating how different computational approaches to the same problem yield different detection capabilities. Similarly, Ericsson has positioned its network as an intelligent fabric where uplink traffic could triple over the next five years driven by AI glasses, sensors, and real-time video, a projection that underscores how the growth in real-time video delivery expands the attack surface for CTV fraud schemes targeting live content. The technical challenge of distinguishing legitimate viewer behavior from bot-generated sessions becomes more complex as viewing patterns diversify across devices and content types.