Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-08-12 · source-backed
Load Hijack modifies nothing but router weights in a checkpoint. When a private trigger appears, token-to-expert assignment concentrates on experts co-located on a single GPU, making it a straggler while peers idle (arXiv 2608.10614). Across three MoE families and four corpora: 92.3–95.6% of triggered assignments hit target experts, producing 1.43x time-to-first-token and 0.86x throughput in live expert-parallel serving. It's a supply-chain attack on the serving schedule, invisible to any output-quality check you're running.
Each link below shares sources, entities, or timing with this story.
Shared entity: When / Same source domain / Earlier coverage / Tension / Downstream implication
Both cover When; reported by the same outlet (arxiv.org); earlier When coverage from 2026-08-10.
Shared entities / Same source domain / Earlier coverage
Both cover GPU, MoE; reported by the same outlet (arxiv.org); earlier GPU coverage from 2026-07-25.
Both cover GPU, MoE; reported by the same outlet (arxiv.org); earlier GPU coverage from 2026-07-23.
Shared entity: MoE / Same source domain / Shared topic / Earlier coverage
Both cover MoE; reported by the same outlet (arxiv.org); overlapping topics (expert, serving).
Shared entities / Earlier coverage / Tension
Both cover GPU, MoE; earlier GPU coverage from 2026-04-23; pushes against this story (versus).
Shared entity: When / Same source domain / Earlier coverage / Tension
Both cover When; reported by the same outlet (arxiv.org); earlier When coverage from 2026-08-03.
Both cover When; reported by the same outlet (arxiv.org); earlier When coverage from 2026-07-26.
Shared entity: MoE / Same source domain / Earlier coverage / Downstream implication
Both cover MoE; reported by the same outlet (arxiv.org); earlier MoE coverage from 2026-07-20.