Abstract: A method includes receiving training data including transcribed speech utterances spoken in a general domain, modified speech utterances in a target domain, and unspoken textual utterances corresponding to the transcriptions of the modified speech utterances in the target domain. The modified speech utterances include utterances spoken in the target domain that have been modified to obfuscate one or more classes of sensitive information recited in the utterances. The method also includes generating a corresponding alignment output for each unspoken textual utterance of the received training data using an alignment model. The method also includes training a speech recognition model on the alignment outputs generated for the corresponding to the unspoken textual utterances, the un-transcribed speech utterances, and the transcribed speech utterances to teach the speech recognition model to learn to recognize speech in the target domain and phrases within the one or more classes of sensitive information.

Abstract: Systems, methods, and computer storage media for traffic segmentation in prevention of DDoS attacks are provided. Data associated with one or more users of a particular service or network is collected. Properties associated with the data are identified. In embodiments, the properties are shared with one or more related services. One or more requests are received for the service or related services. The legitimacy of the one or more requests is predicted.

Abstract: Systems, methods, and computer storage media for traffic segmentation in prevention of DDoS attacks are provided. Data associated with one or more users of a particular service or network is collected. Properties associated with the data are identified. In embodiments, the properties are shared with one or more related services. One or more requests are received for the service or related services. The legitimacy of the one or more requests is predicted.

Abstract: Systems, methods, and computer storage media for traffic segmentation in prevention of DDoS attacks are provided. Data associated with one or more users of a particular service or network is collected. Legitimate properties associated with the data are identified. In embodiments, the legitimate properties are shared with one or more related services. One or more requests are received for the service or related services and request properties are identified. The legitimacy of the one or more requests is predicted based on a comparison of the legitimate and request properties.

Abstract: Systems, methods, and computer storage media for traffic segmentation in prevention of DDoS attacks are provided. Data associated with one or more users of a particular service or network is collected. Legitimate properties associated with the data are identified. In embodiments, the legitimate properties are shared with one or more related services. One or more requests are received for the service or related services and request properties are identified. The legitimacy of the one or more requests is predicted based on a comparison of the legitimate and request properties.