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

arXiv:2603.17174 · cs.CR, cs.AI, cs.SE · Submitted 2026-03-17 · Read on arXiv

cs.CR, cs.AI, cs.SE

Submitted: 2026-03-17

Updated: 2026-09-24

Terminology

• Fine-Tuning — 13× in this paper · explained in 5 episodes
• Analyzer — 11× in this paper · explained in 1 episode
• Accuracy — 8× in this paper · explained in 1 episode
• Consistency — 6× in this paper · explained in 3 episodes
• Decode — 6× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Security and Privacy — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Common Weakness Enumeration — 1× in this paper
• F1 Score — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Gradient-based Adversarial Attacks against Text Transformers
• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
• Qwen2.5-Coder Technical Report
• The Stack: 3 TB of permissively licensed source code
• A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
• Code Llama: Open Foundation Models for Code
• StarCoder 2 and The Stack v2: The Next Generation
• Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Universal Adversarial Triggers for Attacking and Analyzing NLP
• BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

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