Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-22 · source-backed
Black-box attack embedding adversarial instructions into natural images overrides multimodal LLM behavior without model access. A new attack surface distinct from text-based prompt injection, relevant to any pipeline processing user-supplied images. Source
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Same source domain / Shared topic / Tension
Linked by a graph relationship (LLM uses OpenAI); reported by the same outlet (arxiv.org); overlapping topics (access, attack, injection, instruction, model).
Simon Willison released LLM / Shared entity: LLM / Shared topic / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (model, prompt).
LLM uses OpenAI / Shared entity: LLM / What happened next / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; picks up the LLM thread on 2026-07-27.
Simon Willison released LLM / Shared entity: LLM / What happened next / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-16.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-18.
Simon Willison released LLM / Same source domain / Shared topic
Linked by a graph relationship (Simon Willison released LLM); reported by the same outlet (arxiv.org); overlapping topics (model, prompt).
LLM uses OpenAI / Shared entity: LLM / What happened next
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; picks up the LLM thread on 2026-07-31.