相关论文: Multimodal Models Meet Presentation Attack Detecti…

This paper presents a deep-learning-based method for iris presentation attack detection (PAD) when iris images are obtained from deceased people. Our approach is based on the VGG-16 architecture fine-tuned with a database of 574…

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity…

The adoption of large-scale iris recognition systems around the world has brought to light the importance of detecting presentation attack images (textured contact lenses and printouts). This work presents a new approach in iris…

Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the robustness of…

Biometrics security is a dynamic research area spurred by the need to protect personal traits from threats like theft, non-authorised distribution, reuse and so on. A widely investigated solution to such threats consists in processing the…

Face recognition systems are widely deployed for biometric authentication. Despite this, it is well-known that, without any safeguards, face recognition systems are highly vulnerable to presentation attacks. In response to this security…

Wearing a mask has proven to be one of the most effective ways to prevent the transmission of SARS-CoV-2 coronavirus. However, wearing a mask poses challenges for different face recognition tasks and raises concerns about the performance of…

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks, capitalizing on their visual semantic comprehension and reasoning capabilities. However, their ability to detect subtle visual spoofing…

Face presentation attack detection plays a critical role in the modern face recognition pipeline. A face presentation attack detection model with good generalization can be obtained when it is trained with face images from different input…

Biometric authentication systems are increasingly being deployed in critical applications, but they remain susceptible to spoofing. Since most of the research efforts focus on modality-specific anti-spoofing techniques, building a unified,…

The introduction of multimodal models is a huge step forward in Artificial Intelligence. A single model is trained to understand multiple modalities: text, image, video, and audio. Open-source multimodal models have made these breakthroughs…

Face Presentation Attack Detection (PAD) has drawn increasing attentions to secure the face recognition systems that are widely used in many applications. Conventional face anti-spoofing methods have been proposed, assuming that testing is…

With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have focused on privacy risks in single-modal models, we…

In a typical face recognition pipeline, the task of the face detector is to localize the face region. However, the face detector localizes regions that look like a face, irrespective of the liveliness of the face, which makes the entire…

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…

An iris recognition system is vulnerable to presentation attacks, or PAs, where an adversary presents artifacts such as printed eyes, plastic eyes, or cosmetic contact lenses to circumvent the system. In this work, we propose an effective…

The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against…