Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
Score
59Why selected
The paper fills a research gap on cognitive heuristics in code vulnerability detection, with rigorous experimental design and revelation of significant security risks, demonstrating high novelty and practical value.
AI commentary
「This study reveals that LLMs in code security tasks are not only error-prone but also susceptible to cognitive biases, posing a significant caution for practices relying on AI for security audits.」
Quick overview
This paper presents the first systematic exploration of cognitive heuristics in LLM-driven code vulnerability detection. The authors introduce a controlled framework that holds the code fixed and varies the surrounding context to trigger three heuristics: halo effect (author attribution), framing effect (task objectives and consequences), and anchoring effect (prior analysis results). Evaluating eight LLMs across three programming languages, they find all models are susceptible. Cross-model average susceptibility is highest for framing at 33.2%, followed by anchoring at 23.5% and halo at 18.4%. Code-level analysis reveals that vulnerabilities requiring semantic reasoning are more susceptible than those identifiable via pattern matching. Models often change their verdict from safe to vulnerable without correctly identifying the vulnerability. A proof-of-concept black-box cognitive attack can suppress up to 97% of detected vulnerabilities. The findings indicate cognitive susceptibility is a consistent and exploitable property of LLM-based vulnerability detection.
- First systematic exploration of cognitive heuristics in LLM-based code vulnerability detection.
- Framing effect shows highest susceptibility (33.2%), followed by anchoring (23.5%) and halo (18.4%).
- Vulnerabilities requiring semantic reasoning are more susceptible than pattern-matching ones.
- Proof-of-concept black-box attack suppresses up to 97% of previously detected vulnerabilities.
Full text
Computer Science > Cryptography and Security
arXiv:2606.30587v1 (cs) [Submitted on 29 Jun 2026]Title:Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
Authors:Asif Shahriar, Hongyu Cai, Hadjer Benkraouda, Gang Wang, Z. Berkay Celik View a PDF of the paper titled Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection, by Asif Shahriar and 4 other authors View PDFAbstract:Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs are susceptible to the same cognitive heuristics that bias human judgment. Yet, no work has investigated whether these heuristics affect a model's assessment of code vulnerabilities. In this paper, we present the first systematic exploration of cognitive heuristics in LLM-driven code vulnerability detection. We introduce a controlled framework that holds the code fixed and only varies the surrounding context to trigger three cognitive heuristics: the halo effect through author attribution, the framing effect through task objectives and consequences, and the anchoring effect through prior analysis results. Within this framework, we evaluate eight LLMs across three programming languages and perform both quantitative and code-level analyses. Our findings demonstrate that all evaluated models are susceptible to these heuristics. Cross-model average susceptibility is highest for framing at 33.2%, followed by anchoring at 23.5% and halo at 18.4%. Code-level analysis reveals that vulnerabilities that require semantic reasoning for detection are more susceptible to cognitive heuristics than those identifiable through pattern matching. Furthermore, models often change their verdict from safe to vulnerable based on the cognitive condition, without accurately identifying the actual vulnerability. To highlight the practical impact, we demonstrate a proof-of-concept black-box cognitive attack that can suppress up to 97% of previously detected vulnerabilities. These findings indicate that cognitive susceptibility is a consistent and exploitable property of LLM-based vulnerability detection.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.30587 [cs.CR] |
| (or arXiv:2606.30587v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2606.30587 Focus to learn more arXiv-issued DOI via DataCite |
Submission history
From: Asif Shahriar [view email][v1] Mon, 29 Jun 2026 17:31:10 UTC (804 KB)
Full-text links:
Access Paper:
-
View a PDF of the paper titled Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection, by Asif Shahriar and 4 other authors
- View PDF
- TeX Source
view license
Current browse context:
cs.CR < prev | next >new | recent | 2026-06 Change to browse by: cs
cs.AI
References & Citations
export BibTeX citation Loading...BibTeX formatted citation
× Data provided by:Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, MediaCode, Data and Media Associated with this Article
alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) DemosDemos
Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related PapersRecommenders and Search Tools
Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) About arXivLabsarXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍，智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6：前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder：面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red：OpenAI通过自我对弈实现AI红队自动化，提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端，大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T，助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.