کتاب کتاب راهنمای توسعه‌دهندگان برای امنیت مدل‌های زبانی بزرگ

چت‌بات‌هایی که بدرفتار می‌شوند

Let’s Talk About Tay • Tay’s Rapid Decline • Why Did Tay Break Bad? • It’s a Hard Problem

ده مورد برتر OWASP برای برنامه‌های کاربردی LLM

About OWASP • The Top 10 for LLM Applications Project • Project Execution • Reception • Keys to Success • This Book and the Top 10 List

معماری‌ها و مرزهای اعتماد

AI, Neural Networks, and Large Language Models: What’s the Difference? • The Transformer Revolution: Origins, Impact, and the LLM Connection • Origins of the Transformer • Transformer Architecture’s Impact on AI • Types of LLM-Based Applications • LLM Application Architecture • Trust Boundaries • The Model • User Interaction • Training Data • Access to Live External Data Sources • Access to Internal Services • Conclusion

تزریق پرامپت

Examples of Prompt Injection Attacks • Forceful Suggestion • Reverse Psychology • Misdirection • Universal and Automated Adversarial Prompting • The Impacts of Prompt Injection • Direct Versus Indirect Prompt Injection • Direct Prompt Injection • Indirect Prompt Injection • Key Differences • Mitigating Prompt Injection • Rate Limiting • Rule-Based Input Filtering • Filtering with a Special-Purpose LLM • Adding Prompt Structure • Adversarial Training • Pessimistic Trust Boundary Definition • Conclusion

آیا مدل زبانی شما بیش از حد می‌داند؟

Real-World Examples • Lee Luda • GitHub Copilot and OpenAI’s Codex • Knowledge Acquisition Methods • Model Training • Foundation Model Training • Security Considerations for Foundation Models • Model Fine-Tuning • Training Risks • Retrieval-Augmented Generation • Direct Web Access • Accessing a Database • Learning from User Interaction • Conclusion

آیا مدل‌های زبانی خواب گوسفندان برقی را می‌بینند؟

Why Do LLMs Hallucinate? • Types of Hallucinations • Examples • Imaginary Legal Precedents • Airline Chatbot Lawsuit • Unintentional Character Assassination • Open Source Package Hallucinations • Who’s Responsible? • Mitigation Best Practices • Expanded Domain-Specific Knowledge • Chain of Thought Prompting for Increased Accuracy • Feedback Loops: The Power of User Input in Mitigating Risks • Clear Communication of Intended Use and Limitations • User Education: Empowering Users Through Knowledge • Conclusion

به هیچ‌کس اعتماد نکن

Zero Trust Decoded • Why Be So Paranoid? • Implementing a Zero Trust Architecture for Your LLM • Watch for Excessive Agency • Securing Your Output Handling • Building Your Output Filter • Looking for PII with Regex • Evaluating for Toxicity • Linking Your Filters to Your LLM • Sanitize for Safety • Conclusion

کیف پول خود را گم نکنید

DoS Attacks • Volume-Based Attacks • Protocol Attacks • Application Layer Attacks • An Epic DoS Attack: Dyn • Model DoS Attacks Targeting LLMs • Scarce Resource Attacks • Context Window Exhaustion • Unpredictable User Input • DoW Attacks • Model Cloning • Mitigation Strategies • Domain-Specific Guardrails • Input Validation and Sanitization • Robust Rate Limiting • Resource Use Capping • Monitoring and Alerts • Financial Thresholds and Alerts • Conclusion

ضعیف‌ترین حلقه را پیدا کنید

Supply Chain Basics • Software Supply Chain Security • The Equifax Breach • The SolarWinds Hack • The Log4Shell Vulnerability • Understanding the LLM Supply Chain • Open Source Model Risk • Training Data Poisoning • Accidentally Unsafe Training Data • Unsafe Plug-ins • Creating Artifacts to Track Your Supply Chain • Importance of SBOMs • Model Cards • Model Cards Versus SBOMs • CycloneDX: The SBOM Standard • The Rise of the ML-BOM • Building a Sample ML-BOM • The Future of LLM Supply Chain Security • Digital Signing and Watermarking • Vulnerability Classifications and Databases • Conclusion

درس گرفتن از تاریخ آینده

Reviewing the OWASP Top 10 for LLM Apps • Case Studies • Independence Day: A Celebrated Security Disaster • 2001: A Space Odyssey of Security Flaws • Conclusion

به فرآیند اعتماد کنید

The Evolution of DevSecOps • MLOps • LLMOps • Building Security into LLMOps • Security in the LLM Development Process • Securing Your CI/CD • LLM-Specific Security Testing Tools • Managing Your Supply Chain • Protect Your App with Guardrails • The Role of Guardrails in an LLM Security Strategy • Open Source Versus Commercial Guardrail Solutions • Mixing Custom and Packaged Guardrails • Monitoring Your App • Logging Every Prompt and Response • Centralized Log and Event Management • User and Entity Behavior Analytics • Build Your AI Red Team • Advantages of AI Red Teaming • Red Teams Versus Pen Tests • Tools and Approaches • Continuous Improvement • Establishing and Tuning Guardrails • Managing Data Access and Quality • Leveraging RLHF for Alignment and Security • Conclusion

چارچوبی کاربردی برای امنیت مسئولانه هوش مصنوعی

Power • GPUs • Cloud • Open Source • Multimodal • Autonomous Agents • Responsibility • The RAISE Framework • The RAISE Checklist • Conclusion