Related papers: Attack-SAM: Towards Attacking Segment Anything Mod…
Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…
Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…
Image segmentation foundation models (SFMs) like Segment Anything Model (SAM) have achieved impressive zero-shot and interactive segmentation across diverse domains. However, they struggle to segment objects with certain structures,…
Segment anything model (SAM) has shown its spectacular performance in segmenting universal objects, especially when elaborate prompts are provided. However, the drawback of SAM is twofold. On the first hand, it fails to segment specific…
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.…
Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…
Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such…
Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…
Semantic segmentation is an important topic in computer vision with many relevant application in Earth observation. While supervised methods exist, the constraints of limited annotated data has encouraged development of unsupervised…
Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…
The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface. While SAM has already been extensively evaluated in various domains, its…
This paper presents the Autonomous Driving Segment Anything Model (AD-SAM), a fine-tuned vision foundation model for semantic segmentation in autonomous driving (AD). AD-SAM extends the Segment Anything Model (SAM) with a dual-encoder and…
Deep learning has been broadly leveraged by major cloud providers, such as Google, AWS and Baidu, to offer various computer vision related services including image classification, object identification, illegal image detection, etc. While…
The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…
Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything…
Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and language models, which incorporate…
Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…
Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…
As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…