Predicting CVSS Metric via Description Interpretation
نویسندگان
چکیده
Cybercrime affects companies worldwide, costing millions of dollars annually. The constant increase threats and vulnerabilities raises the need to handle in a prioritized manner. This prioritization can be achieved through Common Vulnerability Scoring System (CVSS), typically used assign score vulnerability. However, there is temporal mismatch between vulnerability finding assignment, which motivates development approaches aid this aspect. We explore use Natural Language Processing (NLP) models CVSS prediction given descriptions. start by creating dataset from National Database (NVD). Then, we combine text pre-processing vocabulary addition improve model accuracy interpret its reasoning assessing word importance, via Shapley values. Experiments show that combination Lemmatization 5,000-word optimal for DistilBERT, outperforming our experiments NLP methods, achieving state-of-the-art results. Furthermore, specific events (such as an attack on known software) tend influence prediction, may hinder prediction. Combining with mitigates effect, contributing increased accuracy. Finally, binary classes benefit most techniques, particularly when one class much more prominent than other. Our work demonstrates DistilBERT demonstrating applicability deep learning handling. code data are available at https://github.com/Joana-Cabral/.
منابع مشابه
On Metric Temporal Description Logics
We introduce metric temporal description logics (mTDLs) as combinations of the classical description logic ALC with (a) LTL, an extension of the temporal logic LTL with succinctly represented intervals, and (b) metric temporal logic MTL, extending LTL with capabilities to quantitatively reason about time delays. Our main contributions are algorithms and tight complexity bounds for the satisfiab...
متن کاملTensor Field Visualization Using a Metric Interpretation
This chapter introduces a visualization method specifically tailored to the class of tensor fields with properties similar to stress and strain tensors. Such tensor fields play an important role in many application areas such as structure mechanics or solid state physics. The presented technique is a global method that represents the physical meaning of these tensor fields with their central fe...
متن کاملOf Relating the Linguistic Description to an Interpretation of a Literary Work (Poetry)
This article attempts to see, through the structural significances of poetic language, the nature of the split between linguistic description and literary interpretation. Rhythm is the most prominent means of relating form to content in poetic language. The first account of this prominence is seen through identifying its position in the two prosodic forms of metrical and non-metrical poetry. Fo...
متن کاملLexical Clustering and Definite Description Interpretation
We present preliminary results concerning the use of lexical clustering algorithms to acquire the kind of lexical knowledge needed to resolve definite descriptions, and in particular what we call ’inferential’ descriptions. We tested the hypothesis that the antecedent of an inferential description is primarily identified on the basis of its semantic distance from the description; we also tested...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2022
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2022.3179692