Methods from machine learning are used in the design of secure Industrial Control Systems.
Such methods focus on two major areas: detection of intrusions at the network level using …

Autonomous, or self-driving, cars are emerging as the solution to several problems primarily
caused by humans on roads, such as accidents and traffic congestion. However, those …

Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …

Reproducibility is crucial to the advancement of science; it strengthens confidence in
seemingly contradictory results and expands the boundaries of known discoveries …

To mitigate recent insidious backdoor attacks on deep learning models, advances have
been made by the research community. Nonetheless, state-of-the-art defenses are either …

Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary
could tamper with a small number of model parameter bits to break the integrity of DNNs. To …

This work reveals that standard quantization toolkits can be abused to activate a backdoor.
We demonstrate that a full-precision backdoored model which does not have any backdoor …

As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to
adversarial manipulation and backdoor attacks. Backdoored models deviate from expected …

We propose Hashtag, the first framework that enables high-accuracy detection of fault-
injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection …