Hossein Souri

I am a PhD student in Computer Science at Johns Hopkins University. I'm pleased to be advised by Prof. Rama Chellappa and Prof. Tom Goldstein. I'm a Graduate Reseach Assistant at Artificial Intelligence for Engineering and Medicine Lab (AIEM).

Before joining JHU, I obtained my M.S. and B.S. in Electrical and Computer Engineering from University of Maryland, College Park and University of Tehran respectively. During my Masters studies I was a reseach assistant at University of Maryland Institute for Advanced Computer Studies(UMIACS).

Email / GitHub / Google Scholar / Twitter / LinkedIn / CV

Research

My research interest lies between machine learning and computer vision. I'm trying to apply ml topics including adversarial attacks and defenses, self-supervised learning, meta learning, language models, and GANs to computer vision problems such as image classification and segmentation, object detection, face recognition, and image restoration.

	Identification of Attack-Specific Signatures in Adversarial Examples Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa, arXiv, 2021 PDF / arXiv The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same constraints. In this work, we show that different attack algorithms produce adversarial examples which are distinct not only in their effectiveness but also in how they qualitatively affect their victims.
	Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch Hossein Souri, Micah Goldblum, Liam Fowl, Rama Chellappa, Tom Goldstein arXiv, 2021 PDF / arXiv / code Typical backdoor attacks insert the trigger directly into the training data, although the presence of such an attack may be visible upon inspection. We develop a new hidden trigger attack, Sleeper Agent, which employs gradient matching, data selection, and target model re-training during the crafting process. Sleeper Agent is the first hidden trigger backdoor attack to be effective against neural networks trained from scratch. We demonstrate its effectiveness on ImageNet and in black-box settings.
	GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue Pirazh Khorramshahi, Hossein Souri, Rama Chellappa, Soheil Feizi arXiv, 2020 PDF / arXiv / bibtex GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. To tackle this issue, we take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity. We call this approach GANs with Variational Entropy Regularizers (GAN+VER).
	An adversarial learning algorithm for mitigating gender bias in face recognition Prithviraj Dhar, Joshua Gleason, Hossein Souri, Carlos D. Castillo, Rama Chellappa arXiv, 2020 PDF / arXiv / bibtex A novel approach called `Adversarial Gender De-biasing (AGD)' to reduce the strength of gender information in face recognition features.
	ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence Chun Pong Lau, Hossein Souri, Rama Chellappa FG, 2019 (Oral Presentation) PDF / arXiv / bibtex In this work we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image.