Fetching from the wire…
Security2026-06-15 · source-backed
Researchers demonstrated cross-modal adversarial attacks where crafted audio interferes with AI-driven vision applications (arXiv 2606.14658). The unsettling part is the attack surface it opens: a vision model can be knocked off course through sound, which matters for anyone running CV on shared hardware or sensor-rich edge devices. If your threat model only covers the input modality your model "uses," it's incomplete. Co-located sensors are an ingress path.
Each link below shares sources, entities, or timing with this story.
Shared entity: Researchers / Same source domain / Shared topic / What happened next / Downstream implication
Both cover Researchers; reported by the same outlet (arxiv.org); overlapping topics (application, model).
Shared entity: Researchers / Same source domain / Shared topic / Earlier coverage / Tension
Both cover Researchers; reported by the same outlet (arxiv.org); overlapping topics (model, vision).
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (adversarial, attack, channel, model); pushes against this story (but).
Shared entity: Researchers / Same source domain / What happened next / Tension
Both cover Researchers; reported by the same outlet (arxiv.org); picks up the Researchers thread on 2026-06-26.
Shared entity: Researchers / Same source domain / Earlier coverage / Downstream implication
Both cover Researchers; reported by the same outlet (arxiv.org); earlier Researchers coverage from 2026-05-11.
Shared entity: Researchers / Same source domain / Earlier coverage / Tension
Both cover Researchers; reported by the same outlet (arxiv.org); earlier Researchers coverage from 2026-04-22.
Both cover Researchers; reported by the same outlet (arxiv.org); earlier Researchers coverage from 2026-03-14.
Shared entity: Researchers / Same source domain / What happened next
Both cover Researchers; reported by the same outlet (arxiv.org); picks up the Researchers thread on 2026-08-16.