The paper proposes a two-stage robust aggregation framework to detect and mitigate stealthy backdoor attacks in Over-the-air Federated Learning (OTA-FL) systems, effectively maintaining main-task accu…

This paper proposes a model for cross-band CSI reconstruction in multi-band low-altitude wireless systems using radio-frequency metadata and pilot-guided cross-attention.

The paper proposes VerFU, a client-verifiable federated unlearning framework for low-altitude wireless networks that allows devices to ensure the server accurately removes their historical data contri…

This paper derives a method to predict and mitigate intruder dimensions caused by LoRA fine-tuning in deep learning models, improving performance and reducing forgetting.

The paper introduces the Street-legal Physical Adversarial Rim (SPAR), a physically realizable and street-legal white-box attack that significantly degrades the accuracy of modern Automatic License Pl…

CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…

The paper proposes FedPower, a novel differentially private cross-silo Federated Learning framework that uses PowerDP to reconstruct and project client updates into a secure low-rank space, effectivel…

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright prot…

This paper demonstrates that adversarial perturbations possess a low-rank structure, and proposes a two-step method to leverage this property to significantly improve the efficiency and effectiveness…

This paper demonstrates that a proposed lightweight RFID authentication protocol is structurally insecure and susceptible to a multi-session algebraic attack, enabling full compromise of the secret ke…

This paper presents a portable, battery-powered RF capture system using a HackRF One SDR, Raspberry Pi 5, GNSS receiver, and high-speed storage for recording geotagged IQ data in real-world environmen…

LoREnc is a novel, training-free framework that secures Foundation Models (FMs) and LoRA adapters against intellectual property leakage and model recovery attacks by spectrally truncating weights and…

The paper introduces PINSIGHT, a novel methodology that rigorously assesses Wi-Fi PIN code inference attacks by separating environmental effects from typing effects, concluding that current state-of-t…

The paper introduces BFIAttack, a novel attack that exploits Beamforming Feedback Information (BFI) to reconstruct a user's Channel State Information (CSI), thereby compromising Wi-Fi physical-layer s…