Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization

arXiv:2609.05889 · cs.AI, cs.CR, cs.CV · Submitted 2026-09-05 · Read on arXiv

cs.AI, cs.CR, cs.CV

Submitted: 2026-09-05

Updated: 2026-09-05

Comments: Extended version of the paper accepted by ACM CCS 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Joint Pixel-Prompt Optimization — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Robustness — 1× in this paper · explained in 5 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection