Hybrid Architecture for Distributed Intrusion Detection System
Bibliographic record
Abstract
In the field of information security, attack detection and protection of information from intruders become a new area of research now a days. Due to ever changing technologies and modern methodologies intruders use polymorphic mechanism to deception attack. Various attacks like distributed denial of service, goldeneye, user to root, local to user, remote login become the great threat to the network. To take care of information utmost care is taken to provide network security with the help of various Intrusion Detection System (IDS). IDS helps to detect the threats to the network and can provide various strategies to avoid them. Most of the IDS work intelligently to detect the malicious activities or any abnormal behavior in the network. It leads to the detection of attack and prevention actions can be taken to protect information and provide security to the network. This paper presents an intelligent ID which monitors the real time network traffic to observe the behavior of packets. On the basis of observation detection is done for malicious or normal packets. Action is taken by administrator to prevent the network once the attack is detected by IDS. For attack detection ensembling of various classifiers is done such as Support Vector Machine, Na ve Bayes, k Nearest Neighbor, stochastic gradient descent, logistic regression, Random Forest and Decision tree. All classifiers used classification methods to classify packets in malicious and normal category. Preprocessing is done to reduce features for minimizing training time of all classifiers. Variable importance and Gini index techniques are used to reduce features. Reduced features are used by individual classifier to classify packets in proposed hybrid model. Majority algorithm is used to ensemble the results of all individual classifier to give the final class of packet as attack or normal. All the classifiers work in distributed network to classify the attacks. NSL-KDD dataset is used to train the classifiers. Testing of proposed system is done by capturing real time traffic on the network. From results it is observed that ensembling of more classifiers increases the detection accuracy of IDS significantly and reduces the false alarm rate. It also helps in improving the system performance in terms of execution time and detection rate with increased true positive rate.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".