AI RESEARCH
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
arXiv CS.CV
•
ArXi:2605.28609v1 Announce Type: new Forensic vision-language models (VLMs) have recently been developed to detect image tampering and provide natural-language explanations. However, their robustness against adversarial manipulation remains underexplored. Existing adversarial attacks typically aim to flip the model's binary judgment, while the accompanying explanation may still reveal forensic cues and contradict the attacked judgment.