Deepfake has taken the world by storm, triggering a trust crisis. Curren...
The malicious use and widespread dissemination of deepfake pose a signif...
Causal discovery is a powerful technique for identifying causal relation...
With the performance of deep neural networks (DNNs) remarkably improving...
Deep learning classifiers achieve state-of-the-art performance in variou...
Large language models (LLMs) have witnessed a meteoric rise in popularit...
The language models, especially the basic text classification models, ha...
We study an inverse problem for a coupled system of semilinear Helmholtz...
Numerous studies have underscored the significant privacy risks associat...
Diffusion models have emerged as the de-facto technique for image genera...
Machine Learning as a Service (MLaaS) platforms have gained popularity d...
Building benchmarks to systemically analyze different capabilities of vi...
This paper develops and analyzes a stochastic derivative-free optimizati...
Neural networks are susceptible to data inference attacks such as the
me...
Copyright protection of the Federated Learning (FL) model has become a m...
Faced with the threat of identity leakage during voice data publishing, ...
The task of simultaneously reconstructing multiple physical coefficients...
Data valuation is an essential task in a data marketplace. It aims at fa...
Vertical Federated Learning (FL) is a new paradigm that enables users wi...
Hardware supply-chain attacks are raising significant security threats t...
Time series analysis has achieved great success in diverse applications ...
Vetting security impacts introduced by third-party libraries in iOS apps...
Adversarial training has been widely explored for mitigating attacks aga...
We propose a new stochastic gradient descent algorithm for finding the g...
Full waveform inversion (FWI) aims at reconstructing unknown physical
co...
Prioritizing fairness is of central importance in artificial intelligenc...
Recent studies have revealed that deep neural networks (DNNs) are vulner...
The generalization capacity of various machine learning models exhibits
...
Transferability of adversarial examples is of central importance for
att...
Mobile apps are extensively involved in cyber-crimes. Some apps are malw...
Embedded devices are becoming popular. Meanwhile, researchers are active...
Dynamic analysis based on the full-system emulator QEMU is widely used f...
Emulator is widely used to build dynamic analysis frameworks due to its
...
Selective data protection is a promising technique to defend against the...
The rapid growth of Decentralized Finance (DeFi) boosts the Ethereum
eco...
The popularity of Bitcoin benefits a lot from its anonymity. However, th...
Since its debut, SGX has been used in many applications, e.g., secure da...
Flash Loan, as an emerging service in the decentralized finance ecosyste...
This work characterizes the range of the single-quadrant approximate dis...
In Central Differential Privacy (CDP), there is a trusted analyst who
co...
In Internet of Things, where billions of devices with limited resources ...
As one of the representative blockchain platforms, Ethereum has attracte...
Skeleton-based action recognition has attracted increasing attention due...
Recent years have witnessed the bloom development of the human-centered
...
Wireless signal-based gesture recognition has promoted the developments ...
Code reuse attacks are still big threats to software and system security...
This work characterizes, analytically and numerically, two major effects...
We study in this work an integral formulation for the radiative transfer...
Knowledge graph embedding (KGE) is a technique for learning continuous
e...
We performed the first systematic study of a new attack on Ethereum to s...