The network infrastructure of any organization is always under constant threat to a variety of attacks; namely, break-ins, security breach or system misuse. The Network Intrusion Detection System (NIDS) employed in a network detects such penetration attacks and intrusions within a network. Known classes of attacks can be detected easily by performing pattern matching while the unknown attacks are harder to detect. An attempt has been made to design a system using a deep learning approach for intrusion detection that not only learns but also adjusts itself to the patterns not defined earlier. Sparse auto-encoder has been used for unsupervised feature learning. Logistic classifier is then utilized for classification on NSL-KDD dataset. The performance of the system has been measured with respect to accuracy, precision and recall and the results have been found to be very promising for future use and modifications.

The exponential growth of data and our dependence on it has increased security concerns over the protection of data. Various methodologies have been suggested to meet the security services namely; confidentiality, authentication and authorization. The (k:n) secret sharing scheme was recommended to isolate the dependence on a single entity for the safety of data. Random Grids Visual Secret Sharing (RGVSS), a category of a Visual Cryptography Secret Sharing scheme aims at encrypting a secret image into several shares using a simple algorithm. The encrypted information can be revealed by stacking the shares which can be recognized by the Human Visual System (HVS). The proposed VSS scheme exploits the geometrical configuration of the cube without distorting any of the secret information embedded on the shares. The rest of the secrets are decrypted by stacking the cubes and changing the orientation of one of the cube over the fixed one. Each side of the cube encrypts up to four secrets, the first secret can be decrypted by stacking the two cubical shares and rotating the stacked face of the cube at 90 degrees, 180 degrees and 270 degrees, reveals the other three shares respectively The proposed scheme increases the capacity of secret communication avoiding the pixel expansion problem which in turn reduces the overhead of storage and communication significantly without compromising on security and authenticity of the secret information.