The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

Abstract In recent years, Intelligent Transportation Systems (ITS) have seen efficient and
faster development by implementing deep learning techniques in problem domains which …

Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

We are performing the digital transition of industry, living the 4th industrial revolution,
building a new World in which the digital, physical and human dimensions are interrelated in …

Deep learning models have achieved high performance on many tasks, and thus have been
applied to many security-critical scenarios. For example, deep learning-based face …

We construct targeted audio adversarial examples on automatic speech recognition. Given
any audio waveform, we can produce another that is over 99.9% similar, but transcribes as …

Neural networks are vulnerable to adversarial examples and researchers have proposed
many heuristic attack and defense mechanisms. We address this problem through the …

Though deep neural networks have achieved significant progress on various tasks, often
enhanced by model ensemble, existing high-performance models can be vulnerable to …

Although various techniques have been proposed to generate adversarial samples for white-
box attacks on text, little attention has been paid to a black-box attack, which is a more …

An intriguing property of deep neural networks is the existence of adversarial examples,
which can transfer among different architectures. These transferable adversarial examples …