SIP Flooding Attack Detection with a Multi-Dimensional Sketch Design
Bibliographic record
Abstract
The session initiation protocol (SIP) is widely used for controlling multimedia communication sessions over the Internet Protocol (IP). Effectively detecting a flooding attack to the SIP proxy server is critical to ensure robust multimedia communications over the Internet. The existing flooding detection schemes are inefficient in detecting low-rate flooding from dynamic background traffic, or may even totally fail when flooding is launched in a multi-attribute manner by simultaneously manipulating different types of SIP messages. In this paper, we develop an online detection scheme for SIP flooding attacks, by integrating a novel three-dimensional sketch design with the Hellinger distance (HD) detection technique. In our sketch design, each SIP attribute is associated with a two-dimensional sketch hash table, which summarizes the incoming SIP messages into a probability distribution over the sketch table. The evolution of the probability distribution can then be monitored through HD analysis for flooding attack detection. Our three-dimensional design offers the benefit of high detection accuracy even for low-rate flooding, robust performance under multi-attribute flooding, and the capability of selectively discarding the offending SIP messages to prevent the attacks from bringing damages to the network. Furthermore, we design a scheme to control the distribution of the normal traffic over the sketch. Such a design ensures our detection scheme's effectiveness even under the severe distributed denial of service (DDoS) scenario, where attackers can flood over all the sketch table entries. In this paper, we not only theoretically analyze the performance of the proposed detection techniques, but also resort to extensive computer simulations to thoroughly examine the performance.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".