How to Distribute the Detection Load among Virtual Machines to Maximize the Detection of Distributed Attacks in the Cloud?
Bibliographic record
Abstract
Security has been identified to be the principal stumbling-block preventing users and enterprises from moving their businesses to the cloud. The reason is that cloud systems, besides inheriting all the vulnerabilities of the traditional computing systems, appeal to new types of threats engendered mainly by the virtualization concept that allows multiple users' virtual machines (VMs) to share a common computing platform. This broadens the attack space of the malicious users and increases their ability to attack both the cloud system and other co-resident VMs. Motivated by the absence of any approach that addresses the problem of optimal detection load distribution in the domain of cloud computing, we develop a resource-aware maxmin game theoretical model that guides the hypervisor on how the detection load should be optimally distributed among its guest VMs in the real-time. The objective is to maximize the hypervisor's probability of detection, knowing that the attacker is dividing the attack over several VMs to minimize this probability. Experimental results on Amazon EC2 pricing dataset reveal that our model increases the probability of detecting distributed attacks, reduces the false positives, and minimizes the resources wasted during the detection process.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".