CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software
Paper
•
2107.08760
•
Published
Source Code Analysis
-
-
From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
Paper • 2408.02479 • Published -
PurpCode: Reasoning for Safer Code Generation
Paper • 2507.19060 • Published • 2 -
Vulnerability Detection Using Two-Stage Deep Learning Models
Paper • 2305.09673 • Published -
Studying Vulnerable Code Entities in R
Paper • 2402.04421 • Published -
Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation
Paper • 2310.16263 • Published -
Vulnerability Detection with Code Language Models: How Far Are We?
Paper • 2403.18624 • Published -
Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++
Paper • 2407.17053 • Published -
Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding
Paper • 2309.09826 • Published -
A Vulnerability Code Intent Summary Dataset
Paper • 2504.08180 • Published -
Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models
Paper • 2401.07031 • Published -
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
Paper • 2312.02003 • Published -
A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
Paper • 2512.16538 • Published -
White-Basilisk: A Hybrid Model for Code Vulnerability Detection
Paper • 2507.08540 • Published • 1 -
VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
Paper • 2508.18933 • Published -
LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
Paper • 2401.03374 • Published -
Code Structure-Aware through Line-level Semantic Learning for Code Vulnerability Detection
Paper • 2407.18877 • Published -
DeepCode: Open Agentic Coding
Paper • 2512.07921 • Published • 31 -
CodeQA: A Question Answering Dataset for Source Code Comprehension
Paper • 2109.08365 • Published -
PyRadar: Towards Automatically Retrieving and Validating Source Code Repository Information for PyPI Packages
Paper • 2404.16565 • Published -
Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation
Paper • 2412.16135 • Published -
DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection
Paper • 2304.00409 • Published • 1 -
Malicious Source Code Detection Using Transformer
Paper • 2209.07957 • Published -
STraceBERT: Source Code Retrieval using Semantic Application Traces
Paper • 2312.04731 • Published -
Exploiting Novel GPT-4 APIs
Paper • 2312.14302 • Published • 14 -
CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
Paper • 2404.13161 • Published -
Comparing Human and LLM Generated Code: The Jury is Still Out!
Paper • 2501.16857 • Published • 1 -
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
Paper • 2503.01449 • Published • 4 -
Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets
Paper • 2501.02628 • Published -
Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
Paper • 2403.06675 • Published -
Multi-Agent Penetration Testing AI for the Web
Paper • 2508.20816 • Published -
Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
Paper • 2308.10335 • Published -
BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
Paper • 2505.15216 • Published -
Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis
Paper • 2508.14727 • Published -
Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
Paper • 2412.14841 • Published -
Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security
Paper • 2507.19399 • Published • 1 -
An Empirical Study of Vulnerabilities in Python Packages and Their Detection
Paper • 2509.04260 • Published -
SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
Paper • 2410.11096 • Published • 13 -
Generate and Pray: Using SALLMS to Evaluate the Security of LLM Generated Code
Paper • 2311.00889 • Published -
CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Paper • 2501.08200 • Published • 1 -
ARVO: Atlas of Reproducible Vulnerabilities for Open Source Software
Paper • 2408.02153 • Published -
Demystifying RCE Vulnerabilities in LLM-Integrated Apps
Paper • 2309.02926 • Published -
ReCode: Robustness Evaluation of Code Generation Models
Paper • 2212.10264 • Published • 1 -
MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
Paper • 2507.19598 • Published -
The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs
Paper • 2504.11711 • Published -
IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
Paper • 2405.17238 • Published -
QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
Paper • 2511.08462 • Published -
Security Weaknesses of Copilot Generated Code in GitHub
Paper • 2310.02059 • Published -
CodeFort: Robust Training for Code Generation Models
Paper • 2405.01567 • Published -
Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
Paper • 2311.16169 • Published • 1 -
PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Paper • 2511.11019 • Published • 1 -
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Paper • 2411.07781 • Published • 1 -
Can Large Language Models Find And Fix Vulnerable Software?
Paper • 2308.10345 • Published -
Deep Learning based Vulnerability Detection: Are We There Yet?
Paper • 2009.07235 • Published -
On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
Paper • 2411.19508 • Published -
Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity
Paper • 2508.21634 • Published -
CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models
Paper • 2206.00052 • Published • 1 -
Shellcode_IA32: A Dataset for Automatic Shellcode Generation
Paper • 2104.13100 • Published -
A ground-truth dataset of real security patches
Paper • 2110.09635 • Published -
MetaReflection: Learning Instructions for Language Agents using Past Reflections
Paper • 2405.13009 • Published -
SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
Paper • 2510.00240 • Published • 1 -
Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary
Paper • 2306.02546 • Published • 1 -
A Repository-Level Dataset For Detecting, Classifying and Repairing Software Vulnerabilities
Paper • 2401.13169 • Published -
SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
Paper • 2506.11791 • Published -
CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
Paper • 2507.05269 • Published • 1 -
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Paper • 2507.22063 • Published • 2 -
Cross-Domain Evaluation of Transformer-Based Vulnerability Detection on Open & Industry Data
Paper • 2509.09313 • Published • 2 -
How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models
Paper • 2404.09836 • Published -
Agent That Debugs: Dynamic State-Guided Vulnerability Repair
Paper • 2504.07634 • Published -
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Paper • 2506.08885 • Published -
Revisiting Pre-trained Language Models for Vulnerability Detection
Paper • 2507.16887 • Published • 1 -
Leveraging multi-task learning to improve the detection of SATD and vulnerability
Paper • 2501.15934 • Published • 2 -
Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
Paper • 2509.13755 • Published • 19 -
VulDeePecker: A Deep Learning-Based System for Vulnerability Detection
Paper • 1801.01681 • Published -
Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval
Paper • 2407.02395 • Published -
Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Paper • 2501.05258 • Published -
TRACED: Execution-aware Pre-training for Source Code
Paper • 2306.07487 • Published • 1 -
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Paper • 1909.03496 • Published -
An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation
Paper • 2408.09078 • Published -
VulSolver: Vulnerability Detection via LLM-Driven Constraint Solving
Paper • 2509.00882 • Published -
ProSec: Fortifying Code LLMs with Proactive Security Alignment
Paper • 2411.12882 • Published • 2 -
SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models
Paper • 2512.18542 • Published • 2 -
Reasoning with LLMs for Zero-Shot Vulnerability Detection
Paper • 2503.17885 • Published -
VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
Paper • 2512.07533 • Published • 2 -
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Paper • 2103.15543 • Published -
Learning to Quantize Vulnerability Patterns and Match to Locate Statement-Level Vulnerabilities
Paper • 2306.06109 • Published -
Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives
Paper • 2310.01152 • Published