arXiv:2602. 02498v2 Announce Type: replace-cross Abstract: Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale.
arXiv:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.
arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easi...
The paper introduces Safety-aware Contrastive Decoding (SafeCoDe), a lightweight, model‑agnostic framework designed to improve context‑aware safety in Multimodal Large Language Models (MLLMs). SafeCoDe operates in two stages: a contrastive decoding step that highlights tokens sensitive to visual context by contrasting real and Gaussian‑noised images, and a global‑aware token modulation strategy that adjusts refusals based on scene‑level reasoning and predicted safety verdicts. Experiments across various MLLM architectures and safety benchmarks demonstrate that SafeCoDe consistently enhances context‑sensitive refusal behaviors while maintaining model helpfulness.
arXiv:2604. 00310v2 Announce Type: replace-cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.
arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.
arXiv:2606. 31876v1 Announce Type: new Abstract: To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space.
arXiv:2610.00341v1 Announce Type: cross Abstract: As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generat...
arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...
arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.
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.
ReFrame is a training‑free framework that enhances safety alignment for multimodal large language models at test time. It uses two lightweight agents: one generates risk and utility evidence, and the other rewrites prompts and routes images to create a safe proxy before invoking the deployed MLLM. Experiments show that ReFrame improves jailbreak defense, safety awareness, and reduces over‑sensitivity while maintaining multimodal utility.