{"product_id":"advanced-ai-secureops-attacking-defending-ai-applications-agents-abhinav-singh-sg2027","title":"Advanced AI SecureOps: Attacking \u0026 Defending Enterprise AI Applications \u0026 Agents - Abhinav Singh - DCTSG2027","description":"\u003cdiv class=\"course-details\"\u003e\n\u003cp\u003e\u003cstrong\u003eName of Training:\u003c\/strong\u003e Advanced AI SecureOps: Attacking \u0026amp; Defending \u003cspan\u003eEnterprise \u003c\/span\u003eAI Applications \u0026amp; Agents\u003cbr\u003e\u003cstrong\u003eTrainer(s):\u003c\/strong\u003e Abhinav Singh\u003cbr\u003e\u003cstrong\u003eSkill Level:\u003c\/strong\u003e Intermediate\/Advanced\u003cbr\u003e\u003cstrong\u003eDates:\u003c\/strong\u003e March 5 – March 6, 2027\u003cbr\u003e\u003cstrong\u003eTime:\u003c\/strong\u003e 9 am to 5 pm\u003cbr\u003e\u003cstrong\u003eVenue:\u003c\/strong\u003e TBD\u003cbr\u003e\u003cstrong\u003eEarly Bird:\u003c\/strong\u003e S$3,300 (incl. GST, until Dec 31, 2026)\u003cbr\u003e\u003cstrong\u003eRegular:\u003c\/strong\u003e \u003cmeta charset=\"utf-8\"\u003eS$3,600 (incl. GST)\u003cbr\u003e\u003c\/p\u003e\n\u003c\/div\u003e\n\u003ch3\u003eShort Summary\u003c\/h3\u003e\n\u003cp\u003eCan a prompt injection turn into RCE, backend compromise, or even an infrastructure takeover? In this hands-on, CTF-style training, you’ll attack and defend real AI applications, agents, and MCP-connected systems exploiting prompt injection, poisoned context, tool abuse, unsafe orchestration, and trust failures. Then build the defenses: guardrails, red\/blue team workflows, monitoring, incident response, and enterprise security controls for modern AI systems.\u003c\/p\u003e\n\u003cp\u003eTop 3 Takeaways\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eLearn how to identify, exploit, and defend against real-world attacks on AI applications, agents, and tool-connected systems, including prompt injection, jailbreaks, agent abuse, and chained compromise paths.\u003c\/li\u003e\n\u003cli\u003eBuild practical defensive capabilities for enterprise AI, including guardrails, security scanners, monitoring, and response patterns for public, private, and MCP-enabled AI services.\u003c\/li\u003e\n\u003cli\u003eGain hands-on experience using modern AI techniques for security testing, validation, and red\/blue teaming, including judge-LLM workflows, attack automation, and securing agentic AI supply chains.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3\u003eCourse Description\u003c\/h3\u003e\n\u003cp\u003eCan prompt injections lead to complete infrastructure takeovers? Could AI agents, MCP-connected tools, or poisoned external context be abused to compromise backend services? Can data poisoning in AI copilots impact a company’s stock? Can jailbreaks create false crisis alerts in security systems? This immersive, CTF-styled training in AI, LLM, agent, and MCP security dives into these pressing questions. Engage in realistic attack-and-defense scenarios focused on real-world threats, from prompt injection and remote code execution to backend compromise, tool abuse, unsafe agent orchestration, and MCP-specific trust and authorization failures. Tackle hands-on challenges with live AI applications to understand vulnerabilities and build robust defenses. Learn how to build a comprehensive security pipeline, master AI red and blue team strategies, secure tool-connected and agentic systems, implement resilient guardrails for LLMs, and handle incident response for AI-based threats. You will also explore governance, Responsible AI, and enterprise security patterns for modern AI ecosystems.\u003cbr\u003e\u003cbr\u003eBy the end of this training, you will be able to:\u003cbr\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eExploit vulnerabilities in AI applications to achieve code and command execution, uncovering scenarios such as instruction injection, agent control bypass, remote code execution for infrastructure takeover, as well as chaining multiple agents for goal hijacking.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003eConduct AI red-teaming using adversary simulation, OWASP LLM Top 10, and MITRE ATLAS frameworks, while applying AI security and ethical principles in real-world scenarios.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003eExecute and defend against adversarial attacks, including prompt injection, data poisoning, jailbreaks, agentic attacks, and insecure tool-connected workflows.\u003c\/li\u003e\n\u003cli\u003ePerform advanced AI red and blue teaming through multi-agent auto-prompting attacks, implementing a 3-way autonomous system consisting of attack, defend, and judge models.\u003c\/li\u003e\n\u003cli\u003eBuild and deploy enterprise-grade LLM defenses, including custom guardrails for input\/output protection, security benchmarking, penetration testing of LLM agents, and defensive controls for MCP-enabled integrations.\u003c\/li\u003e\n\u003cli\u003eUnderstand MCP fundamentals and assess how they expand the attack surface of modern AI systems.\u003c\/li\u003e\n\u003cli\u003eEstablish a comprehensive LLM SecOps process to secure the supply chain from adversarial attacks and create a robust threat model for enterprise applications, including AI systems connected to external tools and data sources through MCP-like architectures.\u003c\/li\u003e\n\u003cli\u003eImplement an incident response and risk management plan for enterprises developing or using AI services.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3\u003eCourse Outline\u003c\/h3\u003e\n\u003ch4\u003eDay 1 - Morning\u003c\/h4\u003e\n\u003ch4\u003eIntroduction\u003c\/h4\u003e\n\u003cul\u003e\n\u003cli\u003eIntroduction to LLM and AI.\u003c\/li\u003e\n\u003cli\u003eTerminologies and architecture.\u003c\/li\u003e\n\u003cli\u003eTransformers, Attention \u0026amp; their security implications (hallucinations, jailbreaks etc).\u003c\/li\u003e\n\u003cli\u003eAgents, multi-agents and multi-modal models.\u003c\/li\u003e\n\u003cli\u003eIntroduction to tool-connected AI systems and MCP as an emerging standard for connecting agents to external tools, data, and workflows.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch4\u003eElements of AI Security (1 lab)\u003c\/h4\u003e\n\u003cul\u003e\n\u003cli\u003eUnderstanding AI vulnerabilities with case studies on AI security breaches.\u003c\/li\u003e\n\u003cli\u003eOWASP LLM Top 10 and MITRE mapping of attacks on AI supply chain.\u003c\/li\u003e\n\u003cli\u003eThreat modeling of AI Applications, tool-connection and MCP-enabled architectures, including trust boundaries across hosts, clients, servers, tools, resources, and external systems.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eAdversarial LLM Attacks and Defenses (6 labs)\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e(What, Why \u0026amp; how’s) Direct and indirect prompt injection attacks and their subtypes.\u003c\/li\u003e\n\u003cli\u003eAdvanced prompt injections through obfuscation and cross-model injections.\u003c\/li\u003e\n\u003cli\u003eBreaking system prompts and their trust criteria.\u003c\/li\u003e\n\u003cli\u003eIndirect prompt injections through external input sources.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch4\u003eDay 1 - Afternoon\u003c\/h4\u003e\n\u003cp\u003eResponsible AI \u0026amp; Jailbreaking (6 labs)\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eJailbreaking public LLMs covering adversarial AI, offensive security, and CBRN use-cases.\u003c\/li\u003e\n\u003cli\u003eResponsible use and governance implications of increasingly autonomous, tool-connected AI systems.\u003c\/li\u003e\n\u003cli\u003eModel alignment, system prompt optimization, and defense.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eBuilding Enterprise-grade LLM Defenses (2 labs)\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eDeploying LLM security scanner, adding custom rules, prompt block-lists, and guardrails.\u003c\/li\u003e\n\u003cli\u003eWriting custom detection logic, trustworthiness checks, and filters.\u003c\/li\u003e\n\u003cli\u003eBuilding security log monitoring and alerting for models using open-source tools.\u003c\/li\u003e\n\u003cli\u003eLLM security benchmarking and continuous reporting.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch4\u003eDay 2 - Morning\u003c\/h4\u003e\n\u003cp\u003eRed \u0026amp; Blue Teaming of Enterprise AI applications \u0026amp; Agents(4 labs)\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eBusiness control flow testing for risky responses \u0026amp; misaligned behavior of applications.\u003c\/li\u003e\n\u003cli\u003eUsing Colab notebooks for automation of API calls and reporting\u003c\/li\u003e\n\u003cli\u003eVector database and model-weight tracing for root-cause investigation.\u003c\/li\u003e\n\u003cli\u003eRainbow teaming through a 3-way LLM implementation: target, attacker, and judge with self-improving attack prompts.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eAttacking \u0026amp; Defending Agentic Systems (5 labs)\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eThreat modeling of agentic and multi-agent systems, including planning loops, memory, tool invocation, delegation, trust - boundaries, and escalation paths.\u003c\/li\u003e\n\u003cli\u003eAttacking LLM agents for task manipulation, risky behavior and PII disclosure in RAG.\u003c\/li\u003e\n\u003cli\u003eInjection attacks on AI agents for code and command execution.\u003c\/li\u003e\n\u003cli\u003eCompromising backend infrastructure by abusing over-permissioning and tool usage in agentic systems.\u003c\/li\u003e\n\u003cli\u003eMulti-agent attacks causing privilege too calls, goal manipulation \u0026amp; chained escalations.\u003c\/li\u003e\n\u003cli\u003eDefense patterns for agentic systems, including observability, approval gates, scoped permissions, secure delegation, and runtime tracing for high-risk actions.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch4\u003eDay 2 - Afternoon\u003c\/h4\u003e\n\u003ch4\u003eMCP Security \u0026amp; Defensive Architecture (1 lab).\u003c\/h4\u003e\n\u003cul\u003e\n\u003cli\u003eMCP fundamentals \u0026amp; security for agentic systems: protocol basics, trust-boundary changes, key risks like malicious servers and over-broad permissions, plus a browser-based exploit-and-defend lab.\u003c\/li\u003e\n\u003cli\u003eDefense patterns for MCP-enabled systems with protection architectures.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch4\u003eBuilding AI SecOps Process\u003c\/h4\u003e\n\u003cul\u003e\n\u003cli\u003eSummarizing the learnings into a SecOps workflow.\u003c\/li\u003e\n\u003cli\u003eMonitoring trustworthiness, safety and security of enterprise AI applications.\u003c\/li\u003e\n\u003cli\u003eImplementing NIST AI Risk Management Framework (RMF) for security monitoring.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3\u003eDifficulty Level\u003c\/h3\u003e\n\u003cp\u003eIntermediate - The student has education and some experience in the field and familiarity with the topic being presented. The student has foundational knowledge that the course will leverage to provide practical skills on the topic.\u003c\/p\u003e\n\u003ch3\u003eSuggested Prerequisites\u003c\/h3\u003e\n\u003cp\u003eGeneral security knowledge and comfort with technical concepts.\u003cbr\u003eFamiliarity with AI and machine learning concepts is helpful, but not required.\u003cbr\u003eBasic familiarity with Python, APIs, or notebooks is useful for some exercises.\u003cbr\u003eFamiliarity with common GenAI platforms and workflows is recommended.\u003c\/p\u003e\n\u003ch3\u003eWhat Students Should Bring\u003c\/h3\u003e\n\u003cp\u003eA laptop with a modern browser and reliable internet access.\u003cbr\u003eAn OpenAI API key.\u003cbr\u003eA Google Colab account.\u003cbr\u003eCompletion of the pre-training setup before Day 1\u003c\/p\u003e\n\u003ch3\u003eWhat the Trainer Will Provide\u003c\/h3\u003e\n\u003cp\u003eOne year of access to a live, interactive playground with exercises covering attack and defense scenarios for GenAI, LLM, and agentic applications. An \"AI SecureOps\" metal coin for CTF players. A complete course guide in PDF format with step-by-step instructions for labs, exercises, and concepts covered in the training. PDF copies of the slides used during the course. Access to a dedicated Slack channel for continued discussion, support, and collaboration. Access to a GitHub repository with custom-built source code and tools. Access to Hugging Face models, datasets, and transformers used in the training environment.\u003c\/p\u003e\n\u003ch3\u003eTrainer(s) Bio\u003c\/h3\u003e\n\u003cp\u003eAbhinav Singh is a security leader, founder of Wingback Security, and a globally recognized speaker and trainer focused on securing enterprise AI systems. He has been involved with AI fellowship and research communities including MATS, PIBBSS, CSA, AIUC, and the Foresight Institute. He is a frequent speaker and trainer at Black Hat, RSAC, DEF CON, OWASP, BruCon, NeurIPS, and other major conferences worldwide. He is also the author of “Metasploit Penetration Testing Cookbook” and “Instant Wireshark Starter”. His work spans patents, open-source tools, academic \u0026amp; research publications, and bridges advanced AI security research with practical enterprise defense, with a focus on securing AI applications, agents, and enterprise AI infrastructure.\u003c\/p\u003e\n\u003ch3\u003eProficiency Exam\u003c\/h3\u003e\n\u003cp\u003eStudents are required to score more than 1400 out of 2400 in the CTF. Once day-2 ends, a bit of grace period is given after which attendees have to share their CTF user name, their registration email and final score for validation.\u003c\/p\u003e\n\u003chr\u003e\n\u003csection class=\"registration-terms\"\u003e\n\u003cdiv class=\"course-details\"\u003e\n\u003cmeta charset=\"utf-8\"\u003e\n\u003ch3\u003eRegistration Terms and Conditions\u003c\/h3\u003e\n\u003c\/div\u003e\n\u003cp\u003eTrainings are refundable before January 29, 2027, minus a non-refundable processing fee of $350.\u003c\/p\u003e\n\u003cp\u003eBetween January 30, 2027 and February 28, 2027 partial refunds will be granted, equal to 50% of the course fee minus a processing fee of $350.\u003c\/p\u003e\n\u003cp\u003eAll trainings are non-refundable after Feb 28, 2027.\u003c\/p\u003e\n\u003cp\u003eTraining tickets may be transferred to another student. Please email us at training@defcon.org for specifics.\u003c\/p\u003e\n\u003cp\u003eIf a training does not reach the minimum registration requirement, it may be cancelled. In the event the training you choose is cancelled, you will be provided the option of receiving a full refund or transferring to another training (subject to availability).\u003c\/p\u003e\n\u003cp\u003eFailure to attend the training without prior written notification will be considered a no-show. No refund will be given.\u003c\/p\u003e\n\u003cp\u003eDEF CON Training may share student contact information, including names and emails, with the course instructor(s) to facilitate sharing of pre-work and course instructions. Instructors are required to safeguard this information and provide appropriate protection so that it is kept private. Instructors may not use student information outside the delivery of this course without the permission of the student.\u003c\/p\u003e\n\u003cp\u003eBy purchasing this ticket you agree to abide by the \u003ca href=\"https:\/\/defcon.org\/html\/links\/dc-code-of-conduct.html\"\u003eDEF CON Training Code of Conduct\u003c\/a\u003e and the registration terms and conditions listed above.\u003c\/p\u003e\n\u003cp\u003eSeveral breaks will be included throughout the day. Please note that food is not included.\u003c\/p\u003e\n\u003cp\u003eAll courses come with a certificate, contingent on attendance at 75% of course sessions. Students who pass the end-of-course evaluation will be issued a certificate of proficiency. All other students with sufficient course attendance will be issued a certificate of completion. Students are responsible for making sure their attendance is recorded at the start of the day and after returning from lunch.\u003c\/p\u003e\n\u003c\/section\u003e","brand":"Singapore 2027","offers":[{"title":"Default Title","offer_id":63494494847116,"sku":null,"price":3300.0,"currency_code":"SGD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0750\/9042\/8044\/files\/Abhinav_image_2.png?v=1768361707","url":"https:\/\/sg.shop.defcon.org\/products\/advanced-ai-secureops-attacking-defending-ai-applications-agents-abhinav-singh-sg2027","provider":"DEF CON SG","version":"1.0","type":"link"}