Related papers: Demonstration of an Adversarial Attack Against a M…

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study…

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered…

Vision-language pre-training (VLP) models, trained on large-scale image-text pairs, have become widely used across a variety of downstream vision-and-language (V+L) tasks. This widespread adoption raises concerns about their vulnerability…

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…

Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pretraining (CLIP) model has shown remarkable proficiency in understanding natural…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

The widespread adoption of learning-based methods for the LiDAR makes autonomous vehicles vulnerable to adversarial attacks through adversarial \textit{point injections (PiJ)}. It poses serious security challenges for navigation and map…

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference…

Deep learning models, which are increasingly being used in the field of medical image analysis, come with a major security risk, namely, their vulnerability to adversarial examples. Adversarial examples are carefully crafted samples that…

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than 100,000 LLM calls.…

This work shows that it is possible to fool/attack recent state-of-the-art face detectors which are based on the single-stage networks. Successfully attacking face detectors could be a serious malware vulnerability when deploying a smart…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Accurate classification of focal liver lesions is crucial for diagnosis and treatment in hepatology. However, traditional supervised deep learning models depend on large-scale annotated datasets, which are often limited in medical imaging.…

Deep learning networks have demonstrated high performance in a large variety of applications, such as image classification, speech recognition, and natural language processing. However, there exists a major vulnerability exploited by the…

Generalist foundation model has ushered in newfound capabilities in medical domain. However, the contradiction between the growing demand for high-quality annotated data with patient privacy continues to intensify. The utilization of…

While adversarial attacks on vision-and-language pretraining (VLP) models have been explored, generating natural adversarial samples crafted through realistic and semantically meaningful perturbations remains an open challenge. Existing…