Copertina

Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shukla, Shivani, Joshi, Himanshu, Syed, Romilla
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence Computation and Language Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data
di: Hajipour, Hossein, et al.
Pubblicazione: (2024)

A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications
di: Shukla, Shivani, et al.
Pubblicazione: (2025)

Prompting Techniques for Secure Code Generation: A Systematic Investigation
di: Tony, Catherine, et al.
Pubblicazione: (2024)

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
di: Ren, Qibing, et al.
Pubblicazione: (2024)

Constrained Decoding for Secure Code Generation
di: Fu, Yanjun, et al.
Pubblicazione: (2024)

Instruction Tuning for Secure Code Generation
di: He, Jingxuan, et al.
Pubblicazione: (2024)

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
di: Chen, Junkai, et al.
Pubblicazione: (2025)

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
di: Chen, Yen-Shan, et al.
Pubblicazione: (2026)

The Road of Adaptive AI for Precision in Cybersecurity
di: Garg, Sahil
Pubblicazione: (2025)

Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward
di: Xie, Xuan, et al.
Pubblicazione: (2024)

LUNA: A Model-Based Universal Analysis Framework for Large Language Models
di: Song, Da, et al.
Pubblicazione: (2023)

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
di: Dong, Yihong, et al.
Pubblicazione: (2024)

Automata-Based Steering of Large Language Models for Diverse Structured Generation
di: Luan, Xiaokun, et al.
Pubblicazione: (2025)

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale
di: Garg, Ayush, et al.
Pubblicazione: (2026)

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
di: Wang, Peiran, et al.
Pubblicazione: (2025)

Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
di: Gajjar, Jugal
Pubblicazione: (2026)

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
di: Charoenwet, Wachiraphan, et al.
Pubblicazione: (2026)

PurpCode: Reasoning for Safer Code Generation
di: Liu, Jiawei, et al.
Pubblicazione: (2025)

AI Code Generators for Security: Friend or Foe?
di: Natella, Roberto, et al.
Pubblicazione: (2024)

We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
di: Spracklen, Joseph, et al.
Pubblicazione: (2024)

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs
di: Kaunismaa, Jackson, et al.
Pubblicazione: (2026)

MILE: A Mutation Testing Framework of In-Context Learning Systems
di: Wei, Zeming, et al.
Pubblicazione: (2024)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
di: Hubinger, Evan, et al.
Pubblicazione: (2024)

UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing
di: He, Yifeng, et al.
Pubblicazione: (2024)

LeCov: Multi-level Testing Criteria for Large Language Models
di: Xie, Xuan, et al.
Pubblicazione: (2024)

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
di: Li, Xu, et al.
Pubblicazione: (2026)

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
di: Wei, Zeming, et al.
Pubblicazione: (2026)

DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models
di: Berabi, Berkay, et al.
Pubblicazione: (2024)

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
di: Liu, Yi, et al.
Pubblicazione: (2026)

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

Cyber Threat Detection and Vulnerability Assessment System using Generative AI and Large Language Model
di: M, Keerthi Kumar., et al.
Pubblicazione: (2026)

A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
di: Høst, Anders Mølmen, et al.
Pubblicazione: (2025)

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
di: Le, Hung, et al.
Pubblicazione: (2024)

Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
di: Improta, Cristina
Pubblicazione: (2024)

Textual analysis of End User License Agreement for red-flagging potentially malicious software
di: Khan, Behraj, et al.
Pubblicazione: (2024)

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
di: Qu, Yubin, et al.
Pubblicazione: (2026)

DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
di: Pathak, Abhijeet, et al.
Pubblicazione: (2025)

Security smells in infrastructure as code: a taxonomy update beyond the seven sins
di: War, Aicha, et al.
Pubblicazione: (2025)

Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection
di: Trad, Fouad, et al.
Pubblicazione: (2025)

Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision
di: Mukherjee, Manisha, et al.
Pubblicazione: (2026)