DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints

Backdoor attack is a type of serious security threat to deep learning models. An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output incorrect prediction if the input is stamped...

A 2m-Range 711uW Body Channel Communication Transceiver Featuring Dynamically-Sampling Bias-Free Interface Front End

Body Channel Communication (BCC) offers a low-loss signal transmission medium for ultra-low-power wearable devices on human body [1]. However, the effective communication range on human body is limited to less than 1m in the state-of-the-art BCC transceivers [2], where the signal loss at the interface of body surface and BCC receiver remains to...

Rural Post-Earthquake Resettlement Mode Choices: Empirical Case Studies of Sichuan, China

Earthquakes occur frequently in rural areas of Sichuan, China, causing huge damage and high mortality. The built environment plays a significant role in providing residents with safe and resilient settlements in such areas. There is yet little research on how rural families in developing countries cope with geological disasters like earthquakes,...

Effect of ethanol concentration on methane hydrate decomposition: MD simulation insights

The controllability of mining is a key factor affecting the commercial application of methane hydrates, and the addition of chemical additives can significantly accelerate the mining process. However, the effect of additive concentration on hydrate decomposition is not yet well understood. In this study, we systematically investigate the...

Tunable visible emission and persistent luminescence of BaGa₂O₄:Cu²⁺

In the field of solid-state luminescence, Cu²⁺ has long been widely acknowledged for its capacity to emit infrared light. However, the occurrence of visible emission from Cu²⁺ ions had been infrequently observed and reported. In this study, we made an intriguing discovery by examining the behavior of Cu²⁺...

Hygrothermal effects on fatigue delamination behavior in composite laminates

Fatigue delamination growth (FDG) is an important failure in composite structures during their long-term operations. Hygrothermal aging can have significant effects on interlaminar resistance. It is therefore really necessary to explore FDG behavior in composite laminates with hygrothermal aging. Dynamic mechanical thermal analysis (DMTA),...

Federated Learning With Heterogeneity-Aware Probabilistic Synchronous Parallel on Edge

With the massive amount of data generated from mobile devices and the increase of computing power of edge devices, the paradigm of Federated Learning has attracted great momentum. In federated learning, distributed and heterogeneous nodes collaborate to learn model parameters. However, while providing benefits such as privacy by design and...