Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation

arXiv:2607.17619 · cs.CR · Submitted 2026-07-20 · Read on arXiv

Yuchen Chen, Wei Cheng, Yuan Xiao, Zhou Yang, Weifeng Sun, Chunrong Fang, Xiang Chen, Baowen Xu, David Lo, Zhenyu Chen

cs.CR

Submitted: 2026-07-20

Comments: Accepted to the 35th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026)

Code: https://github.com/filestack/filestack-python

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 9× in this paper · explained in 3 episodes
• Verification — 8× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Annotator Agreement — 5× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Partial Pattern Update — 4× in this paper
• Contradictory Update — 3× in this paper
• Insecure Pattern Replacement — 3× in this paper
• Semantic Similarity — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Evaluating Large Language Models Trained on Code
• Security of Language Models for Code: A Systematic Literature Review
• Rethinking the Evaluation of Secure Code Generation
• Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• A Survey on Large Language Models for Code Generation
• PurpCode: Reasoning for Safer Code Generation
• Prompt Injection attack against LLM-integrated Applications
• Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs
• From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
• Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
• A Survey on the Memory Mechanism of Large Language Model based Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs