Related papers: V-Attack: Targeting Disentangled Value Features fo…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Recent years have witnessed remarkable progress in developing Vision-Language Models (VLMs) capable of processing both textual and visual inputs. These models have demonstrated impressive performance, leading to their widespread adoption in…

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of…

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel.…

Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the…

In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single…

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks…

While vision-language pre-training model (VLP) has shown revolutionary improvements on various vision-language (V+L) tasks, the studies regarding its adversarial robustness remain largely unexplored. This paper studied the adversarial…

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics,…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

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…

Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing failed adversarial perturbations reveals that the learned…

Adversarial attacks have shown the vulnerability of machine learning models, however, it is non-trivial to conduct textual adversarial attacks on natural language processing tasks due to the discreteness of data. Most previous approaches…

Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability…