Cover Image

Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xia, Catherine, Alalfi, Manar H.
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?
by: Quantrill, Jason, et al.
Published: (2026)

Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
by: Cattell, Sven, et al.
Published: (2024)

What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
by: Ma, Boyang, et al.
Published: (2026)

GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?
by: Amro, Amena, et al.
Published: (2025)

AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset
by: Lbath, Amine, et al.
Published: (2025)

Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
by: Cotroneo, Domenico, et al.
Published: (2023)

When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents
by: Kozak, Matous, et al.
Published: (2025)

Data Quality Issues in Vulnerability Detection Datasets
by: Guo, Yuejun, et al.
Published: (2024)

Enhancing Vulnerability Reports with Automated and Augmented Description Summarization
by: Althebeiti, Hattan, et al.
Published: (2025)

LLM-based Vulnerable Code Augmentation: Generate or Refactor?
by: Ouchebara, Dyna Soumhane, et al.
Published: (2025)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
by: Dziemian, Mateusz, et al.
Published: (2026)

CIPHER: Cryptographic Insecurity Profiling via Hybrid Evaluation of Responses
by: Manolov, Max, et al.
Published: (2026)

Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning
by: Li, Qi, et al.
Published: (2024)

White-Basilisk: A Hybrid Model for Code Vulnerability Detection
by: Lamprou, Ioannis, et al.
Published: (2025)

Automated Vulnerability Detection in Source Code Using Deep Representation Learning
by: Seas, C., et al.
Published: (2026)

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
by: Gajjar, Jugal, et al.
Published: (2025)

Code Vulnerability Detection Across Different Programming Languages with AI Models
by: Humran, Hael Abdulhakim Ali, et al.
Published: (2025)

AI-Based Vulnerability Analysis of NFT Smart Contracts
by: Wang, Xin, et al.
Published: (2025)

CIA+TA Risk Assessment for AI Reasoning Vulnerabilities
by: Aydin, Yuksel
Published: (2025)

Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction
by: Mächtle, Felix, et al.
Published: (2025)

PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
by: Jiang, Ziyou, et al.
Published: (2024)

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency
by: Erdem, Galip Tolga
Published: (2026)

Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning
by: Khan, Arshiya, et al.
Published: (2024)

VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
by: Long, Xiang, et al.
Published: (2025)

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
by: Ferrag, Mohamed Amine, et al.
Published: (2024)

SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
by: Li, Xinghang, et al.
Published: (2025)

Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code
by: Blain, Dominik, et al.
Published: (2026)

Quantifying AI Vulnerabilities: A Synthesis of Complexity, Dynamical Systems, and Game Theory
by: Kereopa-Yorke, B
Published: (2024)

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
by: Yang, Jingxiao, et al.
Published: (2026)

Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis
by: Abtahi, Farhad, et al.
Published: (2025)

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
by: Litvak, Ron
Published: (2026)

A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares
by: Cohen, Stav, et al.
Published: (2024)

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
by: Gasmi, Tarek, et al.
Published: (2025)

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation
by: Syed, Toqeer Ali, et al.
Published: (2025)

Quantifying Security Vulnerabilities: A Metric-Driven Security Analysis of Gaps in Current AI Standards
by: Madhavan, Keerthana, et al.
Published: (2025)

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
by: Ding, Xuwei, et al.
Published: (2026)

How Does Naming Affect LLMs on Code Analysis Tasks?
by: Wang, Zhilong, et al.
Published: (2023)

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
by: Saha, Shoumik, et al.
Published: (2025)

SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
by: Nie, Yuzhou, et al.
Published: (2024)

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering
by: Jelodar, Hamed, et al.
Published: (2026)