5 papers
EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learning
Vladimir Frants, Sos Agaian, Karen Panetta
Deploying deep neural networks on edge devices is often limited by the memory traffic and compute cost of dense linear operators. While quaternion neural networks improve parameter…
ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmography
Vladimir Frants, Sos Agaian, Karen Panetta
Remote photoplethysmography (rPPG) estimates a blood volume pulse (BVP) waveform from facial videos captured by commodity cameras. Although recent deep models improve robustness co…
Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset
Vladimir Frants, Sos Agaian
Adverse-weather image restoration (e.g., rain, snow, haze) models remain highly vulnerable to gradient-based white-box adversarial attacks, wherein minimal loss-aligned perturbatio…
Training-Free Color-Aware Adversarial Diffusion Sanitization for Diffusion Stegomalware Defense at Security Gateways
Vladimir Frants, Sos Agaian
The rapid expansion of generative AI has normalized large-scale synthetic media creation, enabling new forms of covert communication. Recent generative steganography methods, parti…
CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture
Vladimir Frants, Sos Agaian, Karen Panetta +1
Images used in real-world applications such as image or video retrieval, outdoor surveillance, and autonomous driving suffer from poor weather conditions. When designing robust com…