ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Knowledge of Large Language Models and code security”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CRcs.LGApr 17, 2026

Surgical Repair of Insecure Code Generation in LLMs

Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth Garg

This paper identifies the 'Format-Reliability Gap'—where LLMs know about code vulnerabilities but generate insecure code anyway—and proposes a localized, per-vulnerability steering vector fix that sig…

View →
cs.CRcs.AIcs.SEMar 17, 2026

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

Shenao Yan, Shimaa Ahmed, Shan Jin, Sunpreet S. Arora +3 more

The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, v…

View →
cs.CRMar 24, 2026

Leveraging Large Language Models for Trustworthiness Assessment of Web Applications

Oleksandr Yarotskyi, José D'Abruzzo Pereira, João R. Campos

This paper proposes an empirical methodology to automate web application trustworthiness assessment by leveraging Large Language Models (LLMs) to verify adherence to secure coding practices, showing t…

View →
cs.CRMar 25, 2026

Bridging Code Property Graphs and Language Models for Program Analysis

Ahmed Lekssays

The paper introduces codebadger, a Model Context Protocol (MCP) server that integrates Joern's Code Property Graph (CPG) with LLMs, enabling large language models to perform large-scale, semantic prog…

View →
cs.SEcs.AIcs.CRMay 11, 2026

Natural Language based Specification and Verification

Zhaorui Li, Chengyu Song

This paper proposes using large language models (LLMs) to generate and compositionally verify software implementations directly from natural language specifications, showing promising preliminary resu…

View →
cs.PLcs.CRMay 15, 2026

Compile-time Security Analysis and Optimization of Sensitive String Producers

Mike Samuel, Tom Palmer, Shaw Summa, Robert Grayson

The paper proposes a general, compiler-integrated framework for secure content composition that minimizes the syntactic difference between secure and insecure coding practices.

View →
cs.CRcs.AIcs.LGRecentMay 22, 2026

An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods

Mohammed Kharma, Ahmed Sabbah, Mohammad Alkhanafseh, Mohammad Hammoudeh +1 more

The paper empirically evaluates the security quality of LLM-generated code across various prompting methods, finding that while prompting alters the structure of weaknesses, it is insufficient to reli…

View →
cs.CRcs.AIApr 20, 2026

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective

Meifang Chen, Zhe Yang, Huang Nianchen, Yizhan Huang +3 more

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

View →
cs.CRcs.AIRecentJun 1, 2026

Large Byte Model: Teaching Language Models About Compiled Code

Florian Störtz, Catalin-Andrei Stan, Alexandru Dinu, Sandra Servia-Rodríguez +3 more

The paper introduces the first byte-native Large Language Model (LLM) capable of analyzing raw executable binary data, achieving high accuracy in tasks like malware and architecture classification.

View →
cs.SEcs.AIcs.CRApr 10, 2026

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation

Li Huang, Zhongxin Liu, Yifan Wu, Tao Yin +5 more

DeepGuard introduces a novel multi-layer semantic aggregation framework to enhance secure code generation by collecting vulnerability cues from multiple upper layers of LLMs, significantly improving s…

View →
cs.CRcs.AIApr 1, 2026

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

Anubhab Sahu, Diptisha Samanta, Reza Soosahabi

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

View →
cs.SEEmpiricalRecentJul 8, 2026

The Poisoned Chalice of LLM Evaluation Report

Jonathan Katzy, Ali Al-Kaswan, Razvan Mihai Popescu, Zhou Yang

The paper organizes the first Poisoned Chalice of LLM Evaluation Competition to detect a large language model's prior exposure to training data without access to the full training corpus.

View →
cs.CRMay 7, 2026

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption

Jaime Morales, Sergio Pastrana, Juan Tapiador

The paper introduces a systematic benchmark to test LLMs' ability to recover Indicators of Compromise (IoCs) from JavaScript code, finding that while LLMs handle simple obfuscation well, encryption-ba…

View →
cs.CRcs.AIApr 2, 2026

From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks

Murtuza Shahzad, Joseph Wilson, Ibrahim Al Azher, Hamed Alhoori +1 more

The paper introduces a novel, large-scale dataset of vulnerable code snippets linked to CAPEC and CWE, generated using advanced LLMs, to improve automatic vulnerability detection.

View →
cs.SEcs.AIcs.CRMar 31, 2026

Software Vulnerability Detection Using a Lightweight Graph Neural Network

Miles Farmer, Ekincan Ufuktepe, Anne Watson, Hialo Muniz Carvalho +3 more

The paper proposes VulGNN, a lightweight Graph Neural Network (GNN) model, which achieves vulnerability detection performance comparable to large language models (LLMs) while being significantly small…

View →
cs.SEcs.AIcs.CRRecentMay 21, 2026

Security of LLM-generated Code: A Comparative Analysis

Srivathsan G Morkonda, Mahmoud Selim, Hala Assal

This paper empirically evaluates the security of code generated by seven popular LLMs and finds that all evaluated models generate code containing critical or high-severity vulnerabilities.

View →
cs.CRcs.AIRecentJun 2, 2026

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

Wenqi Chen, Ziyan Zhang, Bing Wang, Lin Liu +2 more

The paper introduces Tree-like Self-Play (TSP), a novel framework that treats secure code generation as a fine-grained decision process, significantly improving LLM security by forcing the model to se…

View →
cs.SEcs.AIRecentMay 28, 2026

CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models

Vedant Padwal

The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

View →