George Kesidis

Profiling Memory Vulnerability of Big-Data Applications

2016

Motivated by the increasing popularity of hosting in-memory big-data analytics in cloud, we present a profiling methodology that can understand how different memory subsystems, i.e., cache and memory bandwidth, are susceptible to the impact of …

A Backdoor Attack against 3D Point Cloud Classifiers

2021 · arXiv (Cornell University)

Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks against 3D PC classifiers are all test-time evasion (TTE) attacks …

MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

2022 · arXiv (Cornell University)

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern …