MemCatalyst is a set of data poisoning tools designed to improve data auditing for Vision‑Language Models (VLMs). It introduces two poisoning strategies—Poisoning Text and Poisoning Image—to force VLMs to over‑learn inconsistencies between image features and textual semantics, thereby increasing their vulnerability to membership inference attacks. Experiments on two prominent VLMs show that MemCatalyst significantly boosts MI AUC scores with a small number of poisoned samples while barely affecting overall model performance.
Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards.
Vis-Poison is a novel attack that poisons multimodal retrieval-augmented generation systems by inserting attacker-controlled images as visual evidence, without altering any textual metadata. The attack uses an automated multi-agent approach to create visually plausible poisoned images and has been tested on two multimodal RAG pipelines, four embedding models, and six generation models. In black-box settings, Vis-Poison achieves an end-to-end success rate between 40.16% and 65.40% against 30,000-entry knowledge bases, and remains effective against various multimodal large language models with an average success rate above 60%.
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
arXiv:2608. 09928v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.
arXiv:2607. 22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation.
arXiv:2606. 22437v2 Announce Type: replace-cross Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results.
The paper introduces AttnPrint, a white‑box fingerprinting method that extracts low‑frequency components of cross‑modal attention distributions to identify multimodal large language models (MLLMs). It also presents DistillTrace, a black‑box auditing tool that uses hypothesis testing of MLLM outputs to detect potential model infringement. Experiments on 154 model instances across 19 architectures show that AttnPrint effectively detects derivative models and remains robust to downstream modifications, while DistillTrace reveals distillation relationships under various techniques.
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
arXiv:2607. 13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-Training (RSMT).
arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.