Workshop

AI SecureOps: Attacking & Defending AI Applications & Agents

March 17th & 18th

2 days training by Abhinav Singh
This training will be given in ENGLISH

Normal price: CHF 2000.
Student price: CHF 1500.- (limited availability)

Workshop with certification (16 credit hours)

Great news! If you are part of this workshop you also have access to both days of conference.

Description

Can prompt injections lead to complete infrastructure takeovers?

Could AI agents be exploited to compromise backend services?

Can jailbreaks create false crisis alerts in security systems? I

In multi-agent systems, what if an attacker takes over an agent’s goals, turning other agents into coordinated threats? This immersive, CTF-styled training in AI and LLM 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. Tackle hands-on challenges with actual AI applications & agentic systems to understand vulnerabilities and develop robust defenses.

You’ll learn how to create a comprehensive security pipeline, mastering AI red and blue team strategies, building resilient defenses for AI apps & agents, and handling incident response for AI-based threats. Additionally, implement a Responsible AI (RAI) program to enforce ethical AI standards across enterprise services, fortifying your organization’s AI security foundation.

About the trainer

Abhinav Singh

Abhinav Singh is an esteemed cybersecurity leader & researcher with over a decade of experience across technology leaders, financial institutions, and as an independent trainer and consultant. Author of “Metasploit Penetration Testing Cookbook” and “Instant Wireshark Starter,” his contributions span patents, open-source tools, and numerous publications. Recognized in security portals and digital platforms, Abhinav is a sought-after speaker & trainer at international conferences like Black Hat, RSA, DEFCON, BruCon, and many more, where he shares his deep industry insights and innovative approaches in cybersecurity. He also leads multiple AI security groups at CSA, responsible for coming up with cutting-edge whitepapers and industry reports around safety and security of AI.

Follow the instructor:

LinkedIn | X

Course outline

Introduction
– Introduction to LLM and AI.
– Terminologies and architecture.
– Transformers, Attention & their security implications(hallucinations, jailbreaks etc).
– Agents, multi-agents and multi-modal models.

Elements of AI Security (1 lab)
– Understanding AI vulnerabilities with case studies on AI security breaches.
– OWASP LLM Top 10 and MITRE mapping of attacks on AI supply chain.
– Threat modeling of AI Applications.

Adversarial LLM Attacks and Defenses (6 labs)
– Direct and indirect prompt injection attacks and their subtypes.
– Advanced prompt injections through obfuscation and cross-model injections.
– Breaking system prompts and their trust criteria.
– Indirect prompt injections through external input sources.

Responsible AI & Jailbreaking (6 labs)
– Jailbreaking public LLMs covering adversarial AI, offensive security, and CBRN use-cases.
– Responsible AI frameworks and benchmarks.
– Model alignment, system prompt optimization, and defense.

Building Enterprise-grade LLM Defenses (2 labs)
– Deploying LLM security scanner, adding custom rules, prompt block-lists, and guardrails.
– Writing custom detection logic, trustworthiness checks, and filters.
– Building security log monitoring and alerting for models using open-source tools.
– LLM security benchmarking and continuous reporting.

Red & Blue Teaming of Enterprise AI applications (4 labs)
– Business control flow testing for risky responses & misaligned behavior of applications.
– Using Colab notebooks for automation of API calls and reporting
– Vector database and model-weight tracing for root-cause investigation.
– Rainbow teaming through a 3-way LLM implementation: target, attacker, and judge with self-improving attack prompts.

Attacking & Defending Agentic Systems (5 labs)
– Attacking LLM agents for task manipulation, risky behavior and PII disclosure in RAG.
– Injection attacks on AI agents for code and command execution.
– Compromising backend infrastructure by abusing over-permissioning and tool usage in agentic systems.
– Multi-agent attacks causing privilege too calls, goal manipulation & chained escalations.

Building AI SecOps Process
– Summarizing the learnings into a SecOps workflow.
– Monitoring trustworthiness, safety and security of enterprise AI applications.
– Implementing NIST AI Risk Management Framework (RMF) for security monitoring.

Course requirements

Workshop level

Intermediate

Who should attend

This workshop is ideal for:

Security engineers and security architects
Pentesters and red teamers looking to expand into AI security
Blue team and SOC professionals responsible for detection and response
Cloud and application security engineers
AI / ML engineers involved in deploying or maintaining GenAI applications
Security leaders and practitioners preparing for enterprise AI adoption

Key takeways

By the end of this training, you will be able to:

Exploit 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.
Conduct 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.
Execute and defend against adversarial attacks, including prompt injection, data poisoning, jailbreaks and agentic attacks.
Perform 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.
Develop LLM security scanners to detect and protect against injections, jailbreaks, manipulations, and risky behaviors, as well as defending LLMs with LLMs.
Build and deploy enterprise-grade LLM defenses, including custom guardrails for input/output protection, security benchmarking, and penetration testing of LLM agents.
Establish a comprehensive LLM SecOps process to secure the supply chain from adversarial attacks and create a robust threat model for enterprise applications.
Implement an incident response and risk management plan for enterprises developing or using GenAI services.

Course requirements

Familiarity with AI and machine learning concepts is beneficial but not required.
Ability to run python codes and notebooks.
Familiarity with common GenAI applications like OpenAI.

Hardware materials

A laptop with:

Stable internet connection
Ability to run Python and Jupyter / Colab notebooks
Modern web browser
No local AI models required. Labs are cloud-based
Access credentials and lab environments will be provided during the workshop