Related papers: GeoShield: Safeguarding Geolocation Privacy from V…

Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-language and multimodal models further extend these capabilities by incorporating auxiliary…

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

A robust Multimodal Large Language Model (MLLM) for Earth Observation should maintain consistent interpretation and reasoning under realistic input variations. However, current Remote Sensing MLLMs fail to meet this requirement. Trained on…

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…

As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from crawlers or model developers, fundamentally limiting their…

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal…

In recent decades, 3D morphable model (3DMM) has been commonly used in image-based photorealistic 3D face reconstruction. However, face images are often corrupted by serious occlusion by non-face objects including eyeglasses, masks, and…

The tremendous popularity gained by Online Social Networks (OSNs) raises natural concerns about user privacy in social media platforms. Though users in OSNs can tune their privacy by deliberately deciding what to share, the interaction with…

We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that…

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…

Image-based localization is a core component of many augmented/mixed reality (AR/MR) and autonomous robotic systems. Current localization systems rely on the persistent storage of 3D point clouds of the scene to enable camera pose…

We present PrivLEX, a novel image privacy classifier that grounds its decisions in legally defined personal data concepts. PrivLEX is the first interpretable privacy classifier aligned with legal concepts that leverages the recognition…

Recent advances in text-to-image models have increased the exposure of powerful image editing techniques as a tool, raising concerns about their potential for malicious use. An emerging line of research to address such threats focuses on…

Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder…

Existing solutions to visual simultaneous localization and mapping (V-SLAM) assume that errors in feature extraction and matching are independent and identically distributed (i.i.d), but this assumption is known to not be true -- features…

Recent advances in protecting node privacy on graph data and attacking graph neural networks (GNNs) gain much attention. The eye does not bring these two essential tasks together yet. Imagine an adversary can utilize the powerful GNNs to…

Localization in mobile networks has been widely applied in many scenarios. However, an entity responsible for location estimation exposes both the target and anchors to potential location leakage at any time, creating serious security…

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense…

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…