Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code

• URL: http://arxiv.org/abs/2604.12088v1
• Date: Mon, 13 Apr 2026 21:52:57 GMT
• Title: Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code
• Abstract summary: Large language models (LLMs) for code generation are typically evaluated on functional correctness alone.<n>We propose NLSafety-Utility Duality Score (SUDS), a metric that unifies code utility, safety adherence, and warning awareness into a single score.
• Score: 6.664505682266256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) for code generation are typically evaluated on functional correctness alone, overlooking whether generated code propagates harmful content embedded in the prompt. Prior work has shown that most Code LLMs reproduce offensive identifiers from injected renaming instructions without warning, yet existing approaches focus on detecting harmful content, neglecting functional correctness. Grounded in the Theory of Dual Channel Constraints (which states that code is a dual-channel medium combining an algorithmic (AL) channel for machine execution and a natural language (NL) channel for human communication, creating a unique safety-utility trade-off where a model must balance functional execution with responsible communication), we propose NLSafety-Utility Duality Score (SUDS), a metric that unifies code utility, safety adherence, and warning awareness into a single score across 12 ranked response scenarios, and Dual Reasoning (DR), a structured inference-time technique that requires an explicit safety audit and task-grounded code review before code generation. Evaluated on five LLMs across two benchmarks augmented with harmful keyword injections (820 and 2,135 samples), DR consistently achieves the highest SUDS across all models, improving mean SUDS by 1.32$\times$ to 3.42$\times$ over the baseline, while chain-of-thought prompting yields negligible safety gains and a safety-aware prompt provides only partial improvement. Further analysis reveals that DR's effectiveness scales with model capacity, that the one-shot exemplar primarily stabilizes output format for smaller models, and that structured reasoning cannot compensate for models with limited safety vocabularies.

Related papers

• Interpreting and Steering for Safe and Correct Code Generation [11.245452623181398]
  We study how code safety-vs.vulnerability is represented or driven by components in large language models (LLMs)<n>We introduce CodeSec-Pairs, a dataset of 9,342 Python safe-and-vulnerable contrastive code pairs.<n>We propose DuoSteer, a double-steering approach that simultaneously applies safety and code-correctness steering to attention heads.
  arXiv  Detail & Related papers  (2026-08-30T20:30:14Z)
• Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs [46.747768845221735]
  We show that mutations as small as a single-character change can flip generated code from secure to vulnerable.<n>Results show that input-handling flaws can be caught before generation while secure-defaults flaws require intervention during decoding.
  arXiv  Detail & Related papers  (2026-05-28T10:30:28Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization [50.71047638695205]
  Reasoning language models (RLMs) are increasingly used in programming.<n>Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code.<n>We present SecPI, a fine-tuning pipeline that teaches RLMs to internalize structured security reasoning.
  arXiv  Detail & Related papers  (2026-04-04T04:29:11Z)
• Robust Multimodal Safety via Conditional Decoding [52.92816441364308]
  Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.<n>We propose a simple conditional decoding strategy, CASA, that utilizes internal representations of MLLMs to predict a binary safety token before response generation.
  arXiv  Detail & Related papers  (2026-03-31T23:19:50Z)
• Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model [60.60587869092729]
  Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment.<n>We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation.
  arXiv  Detail & Related papers  (2026-02-07T07:42:07Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Countermind: A Multi-Layered Security Architecture for Large Language Models [0.0]
  This paper proposes Countermind, a multi-layered security architecture intended to shift defenses from a reactive, post hoc posture to a proactive, pre-inference, and intra-inference enforcement model.<n>The architecture proposes a fortified perimeter designed to structurally validate and transform all inputs, and an internal governance mechanism intended to constrain the model's semantic processing pathways before an output is generated.
  arXiv  Detail & Related papers  (2025-10-13T18:41:18Z)
• Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models [7.422627253922975]
  We introduce Certifiable Safe-RLHF, a cost model trained on a large-scale corpus to assign semantically grounded safety scores.<n>With an appropriately scaled penalty, feasibility of the safety constraints can be guaranteed, eliminating the need for dual-variable updates.<n> Empirical evaluation demonstrates that CS-RLHF outperforms state-of-the-art model responses rendering at-least 5 times efficient against nominal and jail-breaking prompts.
  arXiv  Detail & Related papers  (2025-10-03T21:24:41Z)
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [64.32925552574115]
  ARMOR is a large language model that analyzes jailbreak strategies and extracts the core intent.<n> ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks.
  arXiv  Detail & Related papers  (2025-07-14T09:05:54Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion [117.178835165855]
  This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs. Our studies reveal a new and universal safety vulnerability of these models against code input. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization.
  arXiv  Detail & Related papers  (2024-03-12T17:55:38Z)
• Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models [1.5457286059556397]
  We propose a reinforcement learning-based method for security hardening and strengthening of generated code from Large Language Models (LLMs) In this work, we propose a reinforcement learning-based method for program-specific repair with the combination of semantic and syntactic reward mechanisms that focus heavily on adding security and functional measures in the code, respectively.
  arXiv  Detail & Related papers  (2024-01-13T10:19:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.