SOTAVerified

Vulnerability Detection

Vulnerability detection plays a crucial role in safeguarding against these threats by identifying weaknesses and potential entry points that malicious actors could exploit. Through advanced scanning techniques and penetration testing, vulnerability detection tools meticulously analyze web applications and websites for vulnerabilities such as SQL injection, cross-site scripting (XSS), and insecure authentication mechanisms.

By proactively identifying and addressing vulnerabilities, organizations can strengthen their online security posture and mitigate the risk of data breaches, financial loss, and reputational damage. Additionally, vulnerability detection empowers businesses to stay compliant with industry regulations and standards, demonstrating their commitment to safeguarding sensitive information and maintaining the trust of their customers. With the evolving threat landscape and increasingly sophisticated attack vectors, investing in robust vulnerability detection measures is paramount for staying one step ahead of cyber threats and ensuring the resilience of web-based platforms and services.

Papers

Showing 51–75 of 216 papers

TitleStatusHype
SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability AnalysisCode0
The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code ClassificationCode0
SAFE: Self-Attentive Function Embeddings for Binary SimilarityCode0
VulDeePecker: A Deep Learning-Based System for Vulnerability DetectionCode0
Reasoning with LLMs for Zero-Shot Vulnerability DetectionCode0
Are Sparse Autoencoders Useful for Java Function Bug Detection?Code0
Program Semantic Inequivalence Game with Large Language ModelsCode0
MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge TranslationCode0
Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security PerspectiveCode0
Multi-role Consensus through LLMs Discussions for Vulnerability DetectionCode0
Responsible Development of Offensive AICode0
Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG EvaluationCode0
Leveraging Generative AI to Enhance Automated Vulnerability ScoringCode0
LLMs in Software Security: A Survey of Vulnerability Detection Techniques and InsightsCode0
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning DataCode0
Enhancing Large Language Models with Faster Code Preprocessing for Vulnerability DetectionCode0
DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilitiesCode0
Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive LearningCode0
eyeballvul: a future-proof benchmark for vulnerability detection in the wildCode0
Machine Learning Techniques for Python Source Code Vulnerability DetectionCode0
Revisiting the Performance of Deep Learning-Based Vulnerability Detection on Realistic DatasetsCode0
Automated Vulnerability Detection in Source Code Using Quantum Natural Language Processing—0
Deep-Learning-based Vulnerability Detection in Binary Executables—0
An Empirical Study of Deep Learning Models for Vulnerability Detection—0
DCDetector: An IoT terminal vulnerability mining system based on distributed deep ensemble learning under source code representation—0
Show:102550
← PrevPage 3 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Reveal Model - Tested on Reveal (Training on Devign + VulScribeR 20K + Extra Cleans)F1 Score26.18—Unverified
2Devign Model - Tested on Reveal (Training on Devign + VulScribeR 20K + Extra Cleans)F1 Score24.99—Unverified
3Reveal Model - Tested on Bigvul (Training on Devign + VulScribeR 20K + Extra Cleans)F1 Score18.98—Unverified
4Devign Model - Tested on Bigvul (Training on Devign + VulScribeR 20K + Extra Cleans)F1 Score18.51—Unverified
5LineVul - Tested on Reveal (Training on Devign + VulScribeR 20K + Extra Cleans)F1 Score17.38—Unverified
6LineVul - Tested on BigVul (Training on Devign + VulScribeR 20K+ Extra Cleans)F1 Score16.23—Unverified
#ModelMetricClaimedVerifiedStatus
1WizardCoderAUC0.86—Unverified
2ContraBERTAUC0.85—Unverified