Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to ...Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to have lower performance, in comparison to the English language. In this paper, we tackle this challenging issue by incorporating multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance. Specifically, we regard entity type distribution as language independent and use bilingual lexicons to bridge cross-lingual semantic mapping. Then, we jointly apply word-level cross-lingual mutual influence and entity-type level monolingual word distributions to enhance low resource name tagging. Experiments on three languages demonstrate the effectiveness of this neural architecture： for Chinese,Uzbek, and Turkish, we are able to yield significant improvements in name tagging over all previous baselines.展开更多
Radio frequency identification （RFID） systems suffer many security risks because they use an insecure wireless communication channel between tag and reader. In this paper, we analyze two recently proposed RFID authe...Radio frequency identification （RFID） systems suffer many security risks because they use an insecure wireless communication channel between tag and reader. In this paper, we analyze two recently proposed RFID authentication protocols. Both protocols are vulnerable to tag information leakage and untraceability attacks. For the attack on the first protocol, the adversary only needs to eavesdrop on the messages between reader and tag, and then perform an XOR operation. To attack the second protocol successfully, the adversary may execute a series of carefully designed challenges to determine the tag＇s identification.展开更多
基金supported by the National High-Tech Development(863)Program of China(No.2015AA015407)the National Natural Science Foundation of China(Nos.61632011 and 61370164)
文摘Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to have lower performance, in comparison to the English language. In this paper, we tackle this challenging issue by incorporating multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance. Specifically, we regard entity type distribution as language independent and use bilingual lexicons to bridge cross-lingual semantic mapping. Then, we jointly apply word-level cross-lingual mutual influence and entity-type level monolingual word distributions to enhance low resource name tagging. Experiments on three languages demonstrate the effectiveness of this neural architecture： for Chinese,Uzbek, and Turkish, we are able to yield significant improvements in name tagging over all previous baselines.
文摘Radio frequency identification （RFID） systems suffer many security risks because they use an insecure wireless communication channel between tag and reader. In this paper, we analyze two recently proposed RFID authentication protocols. Both protocols are vulnerable to tag information leakage and untraceability attacks. For the attack on the first protocol, the adversary only needs to eavesdrop on the messages between reader and tag, and then perform an XOR operation. To attack the second protocol successfully, the adversary may execute a series of carefully designed challenges to determine the tag＇s identification.
