Large language models (LLMs) have witnessed a meteoric rise in popularity among the
general public users over the past few months, facilitating diverse downstream tasks with …

Recent studies revealed that using third-party models may lead to backdoor threats, where
adversaries can maliciously manipulate model predictions based on backdoors implanted …

Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …

Abstract Data-Free Model Extraction (DFME) aims to clone a black-box model without
knowing its original training data distribution, making it much easier for attackers to steal …

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in
various applications of speech recognition. Recently, a few works revealed that these …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …

Recently, point clouds have been widely used in computer vision, whereas their collection is
time-consuming and expensive. As such, point cloud datasets are the valuable intellectual …

Auditing the use of data in training machine-learning (ML) models is an increasingly
pressing challenge, as myriad ML practitioners routinely leverage the effort of content …

Text-to-image diffusion models are pushing the boundaries of what generative AI can
achieve in our lives. Beyond their ability to generate general images, new personalization …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored
model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the …