STARE uses step-wise RL to attack multimodal models, achieving 68% higher attack success rate while revealing that adversarial optimization concentrates conceptual toxicity early and detail toxicity late in the generation trajectory.
naacl-long.360/
2 Pith papers cite this work, alongside 13 external citations. Polarity classification is still indexing.
2
Pith papers citing it
13
external citations · external index
fields
cs.CR 2years
2026 2representative citing papers
Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.
citing papers explorer
-
STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
STARE uses step-wise RL to attack multimodal models, achieving 68% higher attack success rate while revealing that adversarial optimization concentrates conceptual toxicity early and detail toxicity late in the generation trajectory.
-
Prismata: Confining Cross-Site Prompt Injection in Web Agents
Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.