arXiv:2607. 24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users.
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:2601. 04946v3 Announce Type: replace-cross Abstract: Automatic metrics are widely used to evaluate text-to-image models, often replacing human judgment in benchmarking, model selection, and large-scale data filtering.
arXiv:2512.15052v4 Announce Type: replace-cross Abstract: Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understan...
SAFIRE is a large-scale benchmark for fire and smoke understanding in multimodal large language models (MLLMs), featuring 83,000 captioned images across 20 scenarios and 193,000 multiple-choice VQA questions derived from a 9.7K-image subset. The benchmark evaluates 10 dimensions of performance, from basic perception to higher-order reasoning, and employs a GPT‑5.4-assisted verification pipeline to ensure annotation quality. Experiments on ten open-source MLLMs (8B–38B) reveal an average accuracy of 61.9%, highlighting significant gaps in safety-critical reasoning, while fine-tuning vision encoders on just 7% of SAFIRE data boosts fire-scene classification accuracy from 20.1% to 64.5%. All resources are publicly available at https://risys-lab.github.io/SAFIRE/.
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.
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:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.
arXiv:2608. 04052v1 Announce Type: cross Abstract: Backdoor attacks in multimodal contrastive learning (MCL) have garnered growing attention in recent years, as many downstream tasks critically depend on pre-trained MCL models.
arXiv:2609.39688v1 Announce Type: cross Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment...
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.
The paper introduces MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images across 12 high-risk domains, each paired with a hidden user profile, to evaluate personalized safety in vision‑language models (VLMs). Eight leading VLMs were tested and found to almost always respond directly (86‑99%) without seeking missing context, scoring no higher than 2.6/5 on personalized safety. The authors identify a phenomenon called visual dominance, where visual information enters text representations early and suppresses textual risk signals, and propose PRISM, a lightweight input monitor that predicts when a query should be deferred, achieving 0.978 AUC and outperforming all tested models on the safety‑utility Pareto frontier.
arXiv:2609.00206v1 Announce Type: cross Abstract: Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of...