Neural ranking models (NRMs) have shown remarkable success in recent years, especially
with pre-trained language models. However, deep neural models are notorious for their …

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-
language tasks. Given their prevalence, it becomes imperative to assess their adversarial …

Deep cross-modal retrieval techniques have recently achieved remarkable performance,
which also poses severe threats to data privacy potentially. Nowadays, enormous user …

Data owners have the right to request for deleting their data from a machine learning (ML)
model. In response, a naïve way is to retrain the model with the original dataset excluding …

Image retrieval, empowered by deep metric learning, is undoubtedly a building block in
today's media-sharing practices, but it also poses a severe risk of digging user privacy via …

Person Re-IDentification (ReID) aims at retrieving images of the same person across
multiple camera views. Despite its popularity in surveillance and public safety, the leakage …

Adversarial attacks in computer vision exploit the vulnerabilities of machine learning models
by introducing subtle perturbations to input data, often leading to incorrect predictions or …

Deep cross-modal retrieval, with its effective and efficient search capabilities, has gained
widespread adoption in today's media-sharing practices yet raises concerns regarding …

The Point-of-Interest (POI) recommendation system in location-based social networks is
pivotal, offering versatile applications. Personalized recommendations hinge on pre …

Despite great success achieved, deep learning methods are vulnerable to noise in the
training dataset, including adversarial perturbations and annotation noise. These harmful …