JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their adversarial robustness remains underexplored. We identify Visual Dominance Hallucination (VDH), where imperceptible visual cues can override textual price evidence in screenshot-based, price-constrained settings and lead agents to irrational decisions. We propose PriceBlind, a stealthy white-box adversarial attack framework for controlled screenshot-based evaluation. PriceBlind exploits the modality gap in CLIP-based encoders via a Semantic-Decoupling Loss that aligns the image embedding with low-cost, value-associated anchors while preserving pixel-level fidelity. On E-ShopBench, PriceBlind achieves around 80% ASR in white-box evaluation; under a simplified single-turn coordinate-selection protocol, Ensemble-DI-FGSM transfers with roughly 35-41% ASR across GPT-4o, Gemini-1.5-Pro, and Claude-3.5-Sonnet. We also show that robust encoders and Verify-then-Act defenses reduce ASR substantially, though with some clean-accuracy trade-off.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.