86%Must read
?Must readVote to see the score
Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Forced Deferral Attack uses adversarial image triggers to suppress weak-model confidence and force multimodal LLM cascades to route queries to strong models. It learns universal border triggers via temperature-flattened optimization, consistently increasing unintended strong-model usage across datas
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026
– ReadersNo votes yet
14/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 14 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 1/5