|
|
Analysis of DDoS Backscatter Traffic in Network Flow Data
Marušiak, Martin ; Tisovčík, Peter (referee) ; Žádník, Martin (advisor)
This work focuses on detection of denial of service (DoS) attacks which utilize random spoofing of source IP address in attack packets. These types of attacks lead to generation of side effect in a form of backscatter that can be used to identify victims of such attacks. Backscatter analysis has so far been limited to unused address space ranges referred to as network telescopes. This work therefore proposes a new method of DoS attack detection via backscatter outside of network telescope environment where legitimate user traffic is also present. Furthermore proposed approach uses only abstracted traffic in a form of network flows. Presented method was implemented as part of NEMEA system and tested on real flow data capture provided by CESNET.
|
|
|
Prediction of Protein Solubility
Marušiak, Martin ; Martínek, Tomáš (referee) ; Hon, Jiří (advisor)
Protein solubility is closely related to the usability of proteins in industrial use and research. The successful prediction of solubility would therefore lead to a significant saving of financial resources. This work presents new solubility predictor Solpex based on machine learning that achieved better performance on independent test set than any comparable solubility prediction tool. The predictor implementation was preceded by a study of the biological nature of solubility, evaluation of existing solubility prediction approaches, datasets building, many experiments with novel features and selection of the best features for the predictor. As the most important step in machine learning is the datasets building, this work mainly benefits from own rigorous processing of the main source of solubility data - the TargetTrack database.
|
|
|
Analysis of DDoS Backscatter Traffic in Network Flow Data
Marušiak, Martin ; Tisovčík, Peter (referee) ; Žádník, Martin (advisor)
This work focuses on detection of denial of service (DoS) attacks which utilize random spoofing of source IP address in attack packets. These types of attacks lead to generation of side effect in a form of backscatter that can be used to identify victims of such attacks. Backscatter analysis has so far been limited to unused address space ranges referred to as network telescopes. This work therefore proposes a new method of DoS attack detection via backscatter outside of network telescope environment where legitimate user traffic is also present. Furthermore proposed approach uses only abstracted traffic in a form of network flows. Presented method was implemented as part of NEMEA system and tested on real flow data capture provided by CESNET.
|
|
|
Prediction of Protein Solubility
Marušiak, Martin ; Martínek, Tomáš (referee) ; Hon, Jiří (advisor)
Protein solubility is closely related to the usability of proteins in industrial use and research. The successful prediction of solubility would therefore lead to a significant saving of financial resources. This work presents new solubility predictor Solpex based on machine learning that achieved better performance on independent test set than any comparable solubility prediction tool. The predictor implementation was preceded by a study of the biological nature of solubility, evaluation of existing solubility prediction approaches, datasets building, many experiments with novel features and selection of the best features for the predictor. As the most important step in machine learning is the datasets building, this work mainly benefits from own rigorous processing of the main source of solubility data - the TargetTrack database.
|
|
| |
guest ::
RSS feed.