• Publications
  • Influence
Steganography in Inactive Frames of VoIP Streams Encoded by Source Codec
It is revealed that, contrary to existing thought, the inactive frames of VoIP streams are more suitable for data embedding than the active frames of the streams; that is, steganography in the inactive audio frames attains a largerData embedding capacity than that in the active audio frames under the same imperceptibility. Expand
Dynamic-Hash-Table Based Public Auditing for Secure Cloud Storage
A novel public auditing scheme for secure cloud storage based on dynamic hash table (DHT), which is a new two-dimensional data structure located at a third parity auditor (TPA) to record the data property information for dynamic auditing. Expand
Steganography Integration Into a Low-Bit Rate Speech Codec
A new algorithm is proposed for steganography in low bit-rate VoIP audio streams by integrating information hiding into the process of speech encoding, thus maintaining synchronization between information hiding and speech encoding. Expand
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural Network
This paper proposes an effective online steganalysis method to detect QIM steganography and finds four strong codeword correlation patterns in VoIP streams, which will be distorted after embedding with hidden data. Expand
Neural Metaphor Detecting with CNN-LSTM Model
This model combines CNN and LSTM layers to utilize both local and long-range contextual information for identifying metaphorical information in plain texts to extract metaphors from plain texts at word level. Expand
Towards building a high-quality microblog-specific Chinese sentiment lexicon
Experimental results show that the proposed microblog-specific sentiment lexicon can significantly improve the performance of microblog sentiment analysis and an effective and efficient method to detect the popular use-invented new words in Chinese microblogs is proposed. Expand
THU_NGN at SemEval-2018 Task 1: Fine-grained Tweet Sentiment Intensity Analysis with Attention CNN-LSTM
This work proposes a system based on an attention CNN-LSTM model that is used to extract the long-term contextual information from texts and applies attention techniques to selecting this information. Expand
An Approach of Covert Communication Based on the Adaptive Steganography Scheme on Voice over IP
  • Rui Miao, Y. Huang
  • Computer Science
  • IEEE International Conference on Communications…
  • 5 June 2011
This paper presents an adaptive steganography scheme that selects lower embedding bit rate in the flat segments, while the sharp segments can camouflage more secret message and can be used in real-time VoIP network with high hiding capacity. Expand
An adaptive steganography scheme for voice over IP
This paper presents an adaptive steganography scheme for VoIP that enhances the embedding transparency by taking into account the similarity between Least Significant Bits (LSBs) and embedded messages and introduces the notion of Partial Similarity Value (PSV). Expand
Semi-supervised dimensional sentiment analysis with variational autoencoder
A semi-supervised approach for DSA based on the variational autoencoder model that can effectively improve the performance of DSA with considerably less labeled data is proposed. Expand