Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements

• URL: http://arxiv.org/abs/2605.10133v1
• Date: Mon, 11 May 2026 07:44:37 GMT
• Title: Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
• Abstract summary: Large Language Models (LLMs) are increasingly used for automated software development.<n>In practice, many security requirements are implicit or underspecified, whereas usability requirements are explicit and high-signal.<n>This asymmetry motivates our investigation of usability pressure as a practical attack surface.<n>We formalize this threat as UPAttack and propose U-SPLOIT, an automated framework to craft UPAttack.
• Score: 27.244769549288463
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly used for automated software development, making their ability to preserve secure coding practices critical. In practice, however, many security requirements are implicit or underspecified, whereas usability requirements are explicit and high-signal. This asymmetry motivates our investigation of usability pressure as a practical attack surface: realistic usability-oriented requirements (e.g., new features, performance constraints, or simplicity demands) can cause coding LLMs to satisfy explicit usability goals while silently dropping implicit security constraints -- a form of reward hacking. We formalize this threat as UPAttack and propose U-SPLOIT, an automated framework to craft UPAttack that (i) selects tasks where a model is initially secure, (ii) synthesizes usability pressures by identifying usability rewards of insecure alternatives across three vectors (Functionality, Implementation, Trade-off), and (iii) verifies security regression via both existing test cases and dynamically generated exploit payloads. Across 75 seed scenarios (25 CWEs x 3 cases), spanning multiple languages (Python, C, and JavaScript), U-SPLOIT achieves attack success rates up to 98.1% on multiple state-of-the-art models (e.g., GPT-5.2-chat and Gemini-3-Flash-Preview).

Related papers

• Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models [18.740561845552833]
  Oyster-II is a reinforcement learning-based constructive safety alignment framework.<n>It comprehensively surpasses both Qwen3-14B and its predecessor Oyster-I on safety dimensions.
  arXiv  Detail & Related papers  (2026-07-03T03:19:39Z)
• 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)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations [0.0]
  This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails.<n>SecureCAI reduces attack success rates by 94.7% compared to baseline models.
  arXiv  Detail & Related papers  (2026-01-12T18:59:45Z)
• Categorical Framework for Quantum-Resistant Zero-Trust AI Security [0.0]
  We present a novel integration of post-quantum cryptography (PQC) and zero trust architecture (AZT) to secure AI model.<n>Our framework uniquely models cryptographic access as morphisms and trust policies as functors.<n>We demonstrate its efficacy through a concrete ESP32-based implementation.
  arXiv  Detail & Related papers  (2025-11-25T17:17:24Z)
• Death by a Thousand Prompts: Open Model Vulnerability Analysis [0.06213771671016099]
  Open-weight models provide researchers and developers with foundations for diverse downstream applications.<n>We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities that may impact subsequent fine-tuning and deployment.<n>Our findings reveal pervasive vulnerabilities across all tested models, with multi-turn attacks achieving success rates between 25.86% and 92.78%.
  arXiv  Detail & Related papers  (2025-11-05T07:22:24Z)
• Beyond Algorithmic Proofs: Towards Implementation-Level Provable Security [1.338174941551702]
  We present Implementation-Level Provable Security, a new paradigm that defines security in terms of structurally verifiable resilience against real-world attack surfaces during deployment.<n>We present SEER (Secure and Efficient Encryption-based Erasure via Ransomware), a file destruction system that repurposes and reinforces the encryption core of Babuk ransomware.
  arXiv  Detail & Related papers  (2025-08-02T01:58:06Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)

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.