Scene-conditioned spatial-misdirection and duration-inflation backdoors succeed at 2.5–10% poison ratios on multimodal scanpath predictors and resist five adapted defenses.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
A defense framework detects both subgraph and feature-based graph backdoors by exploiting their lower node-neighborhood feature homophily via neighbor-aware reconstruction loss and robust training.
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.
citing papers explorer
-
Follow My Eyes: Backdoor Attacks on Goal-Directed Scanpath Prediction
Scene-conditioned spatial-misdirection and duration-inflation backdoors succeed at 2.5–10% poison ratios on multimodal scanpath predictors and resist five adapted defenses.
-
Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
A defense framework detects both subgraph and feature-based graph backdoors by exploiting their lower node-neighborhood feature homophily via neighbor-aware reconstruction loss and robust training.
-
TRAP: Tail-aware Ranking Attack for World-Model Planning
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.