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 121130 of 216 papers

TitleStatusHype
CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation0
Evaluation of ChatGPT's Smart Contract Auditing Capabilities Based on Chain of Thought0
Finetuning Large Language Models for Vulnerability DetectionCode2
LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning0
A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research0
Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection0
LLbezpeky: Leveraging Large Language Models for Vulnerability Detection0
Exploring the Limits of ChatGPT in Software Security Applications0
ActiveClean: Generating Line-Level Vulnerability Data via Active Learning0
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly0
Show:102550
← PrevPage 13 of 22Next →

Benchmark Results

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