The paper introduces PrivHAR-Bench, a multi-tier benchmark dataset that standardizes the evaluation of the privacy-utility trade-off in video-based action recognition by applying a graduated spectrum…

This paper introduces a novel Vision Transformer (ViT)-based method for privacy-preserving clothing classification that accurately estimates clothing insulation for secure occupant-centric control sys…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

This paper proposes a novel Simultaneous Data Compression and Encryption (SDCE) system that combines chaotic map-based encryption with Huffman encoding to securely and efficiently transmit large video…

The paper introduces BSGS-Diagonal, a memory-efficient algorithm, and GPU-optimized kernels to significantly accelerate and reduce the resource overhead of encrypted face recognition using Fully Homom…

The paper proposes a privacy-preserving smart surveillance framework that uses a MobileNetV2-based classifier for violence detection and employs decentralized, threshold-based encryption for evidence…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

ComPrivDet is an efficient object detection method that detects privacy objects in compressed video streams by reusing inference results from I-frames, significantly reducing latency and computational…

The paper proposes CEAR, an ensemble-based method that combines empirical and certified defenses to achieve superior provable robustness against adversarial attacks in Deep Neural Networks.

This paper compares PCA and LPC for dimensionality reduction in cyberattack classification, demonstrating that both techniques can achieve substantial feature compression with minimal loss of classifi…

The paper proposes a scalable, privacy-preserving framework for iris recognition using Fully Homomorphic Encryption (FHE), achieving accuracy comparable to cleartext while identifying the computationa…

The paper proposes a Privacy-Preserving Product-Quantization Approximate Nearest Neighbor (PPPQ-ANN) framework that achieves practical performance and strong privacy guarantees for large-scale nearest…

This paper presents a black-box membership inference attack (MIA) against Video Large Language Models (VideoLLMs), demonstrating that they are vulnerable by analyzing generation behavior across varyin…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

This paper demonstrates that the Euston secure inference framework, which uses SVD-based matrix transmission to save bandwidth, leaks private input data by exploiting subspace leakage of random masks.

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection a…

The paper introduces a novel privacy-preserving semantic segmentation method that enables model training and inference using independently encrypted images for each client and image.

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

This paper proposes and demonstrates a method to secure high-performance RDMA data transfers by implementing AES-128 encryption directly within a programmable network switch, maintaining high throughp…