A curated list of vibe coding security references
- Security and Privacy for Artificial Intelligence: Opportunities and Challenges: Addresses adversarial attacks and data privacy concerns; proposes frameworks for securing AI systems and offers practical recommendations for future research.
- Security Risk and Attacks in Artificial Intelligence (AI): A Survey of Security and Privacy: Analyzes multiple attack types on AI systems and offers practical security recommendations; addresses implications for privacy and security in AI development.
- Navigating AI Cybersecurity: Evolving Landscape and Challenges: Examines cyber threats like data poisoning and adversarial attacks; proposes a comprehensive framework for robust AI system design emphasizing adaptive security measures.
- How Secure is Code Generated by ChatGPT?: Investigates security vulnerabilities in AI-generated code with a focus on ethical implications; offers strategies for enhancing security through prompt design.
- AI security in different industries: A comprehensive review of vulnerabilities and mitigation strategies: Analyzes security threats in AI, including adversarial attacks and data privacy; offers industry-specific mitigation strategies and practical recommendations.
- SoK: Frontier AI's Impact on the Cybersecurity Landscape: Analyzes risks of frontier AI with a systematic framework for risk assessment; offers actionable recommendations for improving cybersecurity measures.
- Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies: Analyzes adversarial attacks and data privacy issues in deep learning; proposes risk mitigation strategies for enhanced security in AI systems.
- Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal: Proposes a risk assessment framework for LLMs, identifying significant vulnerabilities and employing established methods like OWASP; includes scenario analysis and stakeholder evaluations.
- Security of AI Agents: Addresses unrecognized security vulnerabilities in AI agents; proposes defense mechanisms with experimental evaluations of their effectiveness.
- AI Risk Management Should Incorporate Both Safety and Security: Addresses vulnerabilities in safety-aligned language models; emphasizes the need for a unified framework to analyze safety and security interplay.
- Towards a Robust and Trustworthy Machine Learning System Development: Proposes a metamodel for threat analysis; addresses vulnerabilities to ML-specific attacks and privacy breaches, enhancing system resilience.
- Toward a Comprehensive Framework for Ensuring Security and Privacy in Artificial Intelligence: Comprehensive framework for AI security and privacy; addresses vulnerabilities and data protection with practical recommendations.
- Security and Privacy for Artificial Intelligence: Opportunities and Challenges: Analyzes adversarial attacks and proposes a systematic defense framework; offers practical recommendations for securing AI technologies.
- LLMs for Cyber Security: New Opportunities: Explores LLMs for vulnerability detection and management; discusses frameworks for safe AI development and industry efforts to mitigate LLM risks.
- Artificial Intelligence as the New Hacker: Developing Agents for Offensive Security: Introduces ReaperAI for simulating cyberattacks; discusses penetration testing methodologies and ethical challenges in AI security.
- Frontiers | A systematic literature review on the impact of AI models on the security of code generation: Examines vulnerabilities in AI-generated code, identifies key security flaws, and discusses mitigation strategies for enhancing secure coding practices.
- Generative AI and Large Language Models for Cyber Security: All Insights You Need: Explores LLM vulnerabilities such as prompt injection and data poisoning; provides mitigation strategies and evaluates performance in cybersecurity applications.
- DeVAIC: A tool for security assessment of AI-generated code: Evaluates security of AI-generated Python code with a focus on vulnerabilities from untrusted datasets; utilizes detection rules based on common security vulnerabilities and OWASP Top 10 categories.
- The Cybersecurity Crisis of Artificial Intelligence: Unrestrained Adoption and Natural Language-Based Attacks: Analyzes vulnerabilities in autoregressive large language models; offers recommendations for enhancing cybersecurity practices in AI development.
- The Promise and Peril of Artificial Intelligence - Violet Teaming Offers a Balanced Path Forward: Addresses adversarial vulnerabilities and dual-use risks in AI; proposes 'violet teaming' framework for enhanced security with practical recommendations.
- Security of AI Agents: Analyzes vulnerabilities in AI agents, addressing confidentiality, integrity, and availability; proposes defense mechanisms for enhanced security.
- The Impact of Artificial Intelligence on Data System Security: Systematic review of AI and system security trends; 79 citations highlight its significance in identifying security challenges in AI development.
- Using AI Assistants in Software Development: A Qualitative Study on Security Practices and Concerns: Investigates security implications of AI-generated code through 27 interviews; emphasizes security-critical tasks like code generation and vulnerability detection.
- Quantifying AI Vulnerabilities: A Synthesis of Complexity, Dynamical Systems, and Game Theory: Proposes a novel framework for evaluating AI security vulnerabilities using interdisciplinary approaches; emphasizes metrics for robustness against adversarial manipulation.
- Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models: Examines security threats in open-source AI, identifying risks and manipulative behaviors; promotes responsible AI use.
- Cybersecurity Risks of AI-Generated Code | Center for Security and Emerging Technology: Identifies categories of risks in AI-generated code, evaluates multiple AI models, and provides recommendations for mitigating vulnerabilities in cybersecurity frameworks.
- Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey | Semantic Scholar: No description available.
- Contextual Agent Security: A Policy for Every Purpose: No description available.
- AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks: No description available.
- Quality Assurance for AI-Based Systems: Overview and Challenges (Introduction to Interactive Session): No description available.
- An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping: No description available.
- (PDF) A Systematic Literature Review on AI Safety: Identifying Trends, Challenges and Future Directions: No description available.
- Understanding and Avoiding AI Failures: A Practical Guide: No description available.
- Artificial intelligence for cybersecurity: Literature review ...: by R Kaur · 2023 · Cited by 515 — This article presents a systematic literature review and a detailed analysis of AI use cases for cybersecurity provisioning.
- AI ASSURANCE | A REPEATABLE PROCESS FOR ASSURING AI-ENABLED SYSTEMS: No description available.
- A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair: No description available.
- Vibe Coded Apps & Security Risks: Discusses vulnerabilities in vibe-coded apps, including weak authentication and database misconfigurations, advocating for AI security agents to safeguard user data.
- A Vibe Coding Security Playbook: Keeping AI-Generated Code Safe: In-depth analysis of AI code vulnerabilities with secure coding alternatives, referencing OWASP Top 10 for comprehensive risk management.
- Vibe Coding: AI-Driven Development and Its Security Implications: Explores AI-powered vibe coding with a focus on security risks; emphasizes the need for strict code reviews to prevent vulnerabilities.
- Security in Vibe Coding: Innovation Meets Risk: Explores AI-assisted coding risks with actionable recommendations; addresses SQL injection vulnerabilities and OWASP compliance challenges.
- 10 Secure Coding Practices You Can Implement Now: Implement 10 actionable secure coding practices, including input validation and authentication management, to enhance application security.
- Impact of Poor Coding Patterns on Security Risks: Explores how common coding mistakes can lead to major security vulnerabilities, urging integration of security in the software development lifecycle.
- Secure Coding Practices to Protect Your Code: Covers critical secure coding strategies to mitigate risks like SQL injections and cross-site scripting; includes best practices such as input validation and data encryption.
- Custom Authentication Scheme Developed in Half a Day: Implemented passwordless sign-in and salted password storage, claiming enhanced security over corporate systems.
- The Importance of Secure Coding in Software Development: Prevents cybersecurity incidents through secure coding practices like input validation and secure storage, enhancing customer trust and reducing long-term security costs.
- How to Write Secure Code: Covers essential secure coding practices with detailed examples and OWASP guidelines to mitigate risks associated with insecure coding.
- Best Practices for Secure Coding in Web Applications: Covers five essential secure coding practices to prevent vulnerabilities, including input validation and authentication; crucial for safeguarding against injection attacks and data breaches.
- Connection Between Coding and Cybersecurity: Explores essential coding practices like reverse engineering and fuzzing for identifying vulnerabilities, crucial for various cybersecurity careers.
- Understanding Secure Coding: Best Practices and Techniques: Eliminate vulnerabilities with secure coding techniques; covers SQL injection and XSS, referencing OWASP and NIST guidelines.
- Cybersecurity Coding Essentials: Explores 13 programming languages crucial for cybersecurity, detailing their applications in enhancing security practices and roles requiring coding expertise.
- Replit — Secure Vibe Coding Made Simple: Integrates security in app development with practices like SQL injection protection and API key management, supported by credible studies.
- GitHub's Use of CodeQL for Enhanced Security: Automated security analyses with CodeQL enable detection of vulnerabilities in code, integrating seamlessly into CI pipelines for improved security practices.
- Remote Code Execution in qmail (CVE-2005-1513): Exploit method bypassing NX and ASLR for malloc-header corruption in qmail, detailing integer overflow vulnerabilities.
- Secure Coding Enhances Development Speed: Boosts developer confidence and fosters a positive security culture, leading to faster project delivery.
- API Security Best Practices: Covers critical measures like using API gateways and centralized OAuth servers to prevent vulnerabilities, referencing OWASP's Top 10 API Security Vulnerabilities.
- 10 Key Predictions: Secure Code Warrior on AI & Secure by Design: Explores AI's impact on secure coding with a focus on 'Secure by Design' principles and the risks of AI-generated code for developers.
- Guidelines for Completing Vendor Security Questionnaires: Streamline your security questionnaire responses using NIST and ISO frameworks to enhance compliance and close deals faster.
- Security Training for Developers in 2024: Enhance developer security awareness with effective training strategies; emphasizes shift-left approach and practical methods like security code reviews.
- Is Annual Secure Coding Training Enough?: Experts recommend a continuous, multi-year secure coding training approach to address vulnerabilities like SQL injection and cross-site scripting, rather than relying on annual sessions.
- The Art of Secure Coding: Encourages developers to pursue secure coding training for building robust software against cyber attacks.
- 2023 Security Cheatsheet: OWASP Top Ten Vulnerabilities: Covers 10 critical security vulnerabilities with detailed mitigation strategies, based on the latest OWASP guidelines.
- "Vibe Coding" 101: What It Is, How It Works, and Why It Matters: No description available.
- What is Vibecode?: No description available.
- What I learned from Vibe Coding: No description available.
- Vibe Coding: The Best Way Of Coding — As Long As You Don’t Have To Maintain Your Code Base: No description available.
- What is Vibe Coding? (Meme Review): No description available.
- Will “vibe coding” eliminate actual programmers? - JavaScript in Plain English: No description available.
- What is vibe coding, exactly?: No description available.
- How Much Horsepower Do You Really Need?: No description available.
- Ask HN: How to deal with AI generated sloppy code: No description available.
- CA01 new design assisted (iA) new 3d model - ZBrushCentral: No description available.