Poisoning and Evasion: Deep Learning-Based NIDS under Adversarial Attacks
Bibliographic record
Abstract
Given their crucial role in protecting networks from numerous security threats, intrusion detection systems are crucial to any cybersecurity architecture. Deep neural networks have recently shown astounding effectiveness and performance in various machine learning applications, including intrusion detection. However, it has been observed that deep learning models are highly susceptible to a wide range of attacks during both the training and testing phases. These attacks can compromise the privacy of deep learning models, such as poisoning attacks that can affect the performance of the target model during the training process and evasion attacks that can undermine the security of these models during the testing phase. Numerous studies have been conducted to understand and mitigate these attacks and to propose more efficient techniques with higher success rates and accuracy in various tasks utilizing deep learning models, such as image classification, face recognition, network intrusion detection, and healthcare applications. Despite the considerable efforts in this area, the network domain still lacks sufficient attention to these attacks and vulnerabilities. This paper aims to address this gap by proposing a framework for adversarial attacks against network intrusion detection systems (NIDS). The proposed framework focuses on poisoning and evasion attacks and tries to combine these attacks. We evaluate the proposed framework on three CIC-IDS2017, CIC-IDS2018, and CIC-UNSW-NB15 datasets.
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 | 0.004 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".