Related papers: A Systematic Study of Cross-Modal Typographic Atta…

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

Multimodal Large Language Models (MLLMs), which integrate vision and other modalities into Large Language Models (LLMs), significantly enhance AI capabilities but also introduce new security vulnerabilities. By exploiting the…

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing…

Small language models (SLMs) have become increasingly prominent in the deployment on edge devices due to their high efficiency and low computational cost. While researchers continue to advance the capabilities of SLMs through innovative…

Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across…

Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and…

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based…

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models…

Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning and visual question and answering. However, similar to…

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal…

Multimodal Large Language Models demonstrate strong performance on multimodal benchmarks, yet often exhibit poor robustness when exposed to spurious modality interference, such as irrelevant text in vision understanding, or irrelevant…

Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders…

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely…