Deep neural networks are known to be vulnerable adversarial attacks. The empirical analysis in our study suggests that attacks tend induce diverse network architectures shift the attention irrelevant regions. Motivated by this observation, we propose a regularization technique which enforces attentions well aligned via knowledge transfer mechanism, thereby encouraging robustness. Resultant mode...

Quantum networks are a new paradigm of complex networks, allowing us to harness networked quantum technologies and develop internet. But how robust is network when its links nodes start failing? We show that based on typical noisy quantum-repeater prone discontinuous phase transitions with respect the random loss operating nodes, abruptly compromising connectivity network, thus significantly li...