相关论文: Alpha-wolves and Alpha-mammals: Exploring Dictiona…

Biometric recognition systems are security systems based on intrinsic properties of their users, usually encoded in high dimension representations called embeddings, which potential theft would represent a greater threat than a temporary…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

The rapid advancement of text-to-image generation systems, exemplified by models like Stable Diffusion, Midjourney, Imagen, and DALL-E, has heightened concerns about their potential misuse. In response, companies like Meta and Google have…

Duplicate records pose significant challenges in customer relationship management (CRM)and healthcare, often leading to inaccuracies in analytics, impaired user experiences, and compliance risks. Traditional deduplication methods rely…

Nowadays, facial recognition systems are still vulnerable to adversarial attacks. These attacks vary from simple perturbations of the input image to modifying the parameters of the recognition model to impersonate an authorised subject.…

Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structured and explicit format. As a result, privacy risks arise,…

The use of the iris as a biometric identifier has increased dramatically over the last 30 years, prompting privacy and security concerns about the use of iris images in research. It can be difficult to acquire iris image databases due to…

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are…

The rise of AI voice-cloning technology, particularly audio Real-time Deepfakes (RTDFs), has intensified social engineering attacks by enabling real-time voice impersonation that bypasses conventional enrollment-based authentication. This…

The task of deepfakes detection is far from being solved by speech or vision researchers. Several publicly available databases of fake synthetic video and speech were built to aid the development of detection methods. However, existing…

Although vision-language pre-training (VLP) models have achieved remarkable progress on cross-modal tasks, they remain vulnerable to adversarial attacks. Using data augmentation and cross-modal interactions to generate transferable…

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…

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

The widespread integration of autoregressive-large language models (AR-LLMs), such as ChatGPT, across established applications, like search engines, has introduced critical vulnerabilities with uniquely scalable characteristics. In this…

With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary…

Face morphing attacks are widely recognized as one of the most challenging threats to face recognition systems used in electronic identity documents. These attacks exploit a critical vulnerability in passport enrollment procedures adopted…

We have witnessed rapid advances in both face presentation attack models and presentation attack detection (PAD) in recent years. Compared to widely studied 2D face presentation attacks (e.g. printed photos and video replays), 3D face…

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which…