Hacking LLM

Virtual Learning:1,990€ + IVA

Duração:

2 dias

Próxima Data:

9 a 10 Mar 2026

Local:

Online

Descrição

The rapid adoption of AI and, specifically, Large Language Models (LLMs), has opened new frontiers in innovation. And in attack surfaces...As companies rush to harness the power of LLMs in applications ranging from customer service to data analytics, they often overlook the emerging security gaps introduced by prompt injection, data poisoning, insecure plugin designs, and more.

Our course directly tackles these new challenges. Over two immersive days, you’ll not only uncover high-impact vulnerabilities that could already be at work within your systems but also learn how to patch them before they result in breaches or critical data leaks. In addition, we regularly update our modules and labs to incorporate the latest security breakthroughs, proof-of-concept exploits, and real-world incidents.

This focus on cutting-edge threats and solutions means that attendees can return year after year for fresh insights, continually refining their ability to secure AI-driven environments as new vulnerabilities emerge.

*PVP por participante. A realização do curso nas datas apresentadas está sujeita a um quórum mínimo de inscrições.

Destinatários

Security Professionals
Back-End / Front-End Developers
System Architects
Product Managers
Anyone directly involved in the integration and application of LLM technologies

Área: Cybersecurity

Inscrição

Programa:

Prompt Engineering

What makes a good prompt
How to write effective prompts
Including reference text in prompt
Few-Shot prompting
How to give AI time to think
Using Delimiters for Clarity and Security

Prompt Injection

Nature of Prompt Injection Vulnerabilities
Direct vs. Indirect Injection
Real-World Exploits
Impact and Consequences
Defense Strategies
Client-Side attacks
Case Study: WannaCry
LAB ACTIVITIES:
- The Math Professor
- Indirect Prompt Injection

ReACT LLM Agent Prompt Injection

Understanding ReACT
Tools Purpose in ReACT
Tool Abuse in Frameworks
RAO Chain Exploitation
Prevention and Mitigation
LAB ACTIVITIES:
- The Bank of NSS

Overreliance in LLM’s

Insecure Output Handing

Defining Insecure Output Handling
Recognizing Vulnerabilities
Simulated Attacks
Impact of Weaknesses
Proactive Measures
LAB ACTIVITIES:
- Report summarization application
- Network analysis agent
- Stock Bot

Training Data Poisoning

LAB ACTIVITIES:
- Adversarial Poisoning Attack Lab
- Injecting Factual Information Lab

Supply Chain Vulnerabilities

Sensitive Information Disclosure

LAB ACTIVITIES:
- Incomplete Filtering lab
- Overfitting / Memorization lab
- Misinterpretation

Insecure Plugin Design

LAB ACTIVITIES:
- Insecure tool usages

Excessive Agency in LLMBased Systems

LAB ACTIVITIES:
- Excessive agency with excessive functionality
- Excessive agency with excessive permissions

Pré-requisitos:

Basic Understanding of AI: A foundational knowledge of AI and LLM principles and applications is essential.
Familiarity with Programming: Some experience with coding, particularly in languages commonly used in AI development (e.g., Python), will be beneficial, though advanced proficiency is not required.
Understanding of cybersecurity concepts: A basic understanding of cybersecurity threats and mitigation strategies will be advantageous.
Laptop: AI labs are served in the cloud, access to python IDE is via Jupiter notebooks, the only hardware requirement is access to the latest version of Chrome or Firefox.

Inscrição