8 papers
Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming
Hossein Khalili, Philip Do, Alexander Vilesov +3
Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame by frame, RGB-D volumetric pipeli…
Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference
Sayedeh Leila Noorbakhsh, Hossein Khalili, Nader Sehatbakhsh
Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers. However, transm…
SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models
Hossein Khalili, Seongbin Park, Venkat Bollapragada +1
As vision-based machine learning models are increasingly integrated into autonomous and cyber-physical systems, concerns about (physical) adversarial patch attacks are growing. Whi…
To See or Not to See -- Fingerprinting Devices in Adversarial Environments Amid Advanced Machine Learning
Justin Feng, Amirmohammad Haddad, Nader Sehatbakhsh
The increasing use of the Internet of Things raises security concerns. To address this, device fingerprinting is often employed to authenticate devices, detect adversaries, and ide…
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Hossein Khalili, Seongbin Park, Vincent Li +4
Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learnin…
Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?
Alexander Vilesov, Yuan Tian, Nader Sehatbakhsh +1
The exponential progress in generative AI poses serious implications for the credibility of all real images and videos. There will exist a point in the future where 1) digital cont…
SoK: A Study of the Security on Voice Processing Systems
Robert Chang, Logan Kuo, Arthur Liu +1
As the use of Voice Processing Systems (VPS) continues to become more prevalent in our daily lives through the increased reliance on applications such as commercial voice recogniti…
Security and Privacy Considerations for Machine Learning Models Deployed in the Government and Public Sector (white paper)
Nader Sehatbakhsh, Ellie Daw, Onur Savas +2
As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by r…