相关论文: Exploiting Alpha Transparency In Language And Visi…

Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…

In recent years, various out-of-band covert channels have been proposed that demonstrate the feasibility of leaking data out of computers without the need for network connectivity. The methods proposed have been based on different type of…

Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Air-gapped computers are systems that are kept isolated from the Internet since they store or process sensitive information. In this paper, we introduce an optical covert channel in which an attacker can leak (or, exfiltlrate) sensitive…

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.…

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

Biometric systems based on Machine learning and Deep learning are being extensively used as authentication mechanisms in resource-constrained environments like smartphones and other small computing devices. These AI-powered facial…

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…

It is increasingly easy to automatically swap faces in images and video or morph two faces into one using generative adversarial networks (GANs). The high quality of the resulted deep-morph raises the question of how vulnerable the current…

Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…

This paper introduces a novel attack vector that leverages website cloaking techniques to compromise autonomous web-browsing agents powered by Large Language Models (LLMs). As these agents become more prevalent, their unique and often…

The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of…

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Knowing more about the data used to build AI systems is critical for allowing different stakeholders to play their part in ensuring responsible and appropriate deployment and use. Meanwhile, a 2023 report shows that data transparency lags…

We present a new type of backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) that has been previously unstudied. In particular, we examine the application of facial recognition. Deep learning techniques are…

Recent years have seen fast development in synthesizing realistic human faces using AI technologies. Such fake faces can be weaponized to cause negative personal and social impact. In this work, we develop technologies to defend individuals…