Skip to content

Back to the catalog

8kSec AI/LLM Exploitation Labs
academy.8ksec.iocourse

8kSec AI/LLM Exploitation Labs

8kSec's AI/LLM Exploitation Labs is a set of hands-on CTF-style challenges covering real attack classes against AI systems: prompt-injection to manipulate an LLM essay grader and a workspace assistant into granting admin access, crafting adversarial images to bypass an MNIST-based ML authentication vault, extracting a "secret" encryption key from an n8n/OpenAI chatbot via conversation alone, exploiting a remote MCP server (via Cursor) for path traversal to read /etc/passwd, poisoning a training CSV to backdoor a spam classifier, detecting neural network backdoors in CIFAR-10 models, spotting a malicious MCP skill with a data-exfiltration payload, and identifying "ghost record" membership-inference leakage in a supply-chain-compromised model. Each challenge maps to a distinct AI security technique (prompt injection, adversarial examples, model/data poisoning, MCP tool abuse, membership inference) and offers a free certification on completion.

TL;DR Hands-on lab suite covering prompt injection, adversarial ML, model backdoors, data poisoning, and MCP exploitation, with a free completion certificate.
Open original ↗

Technologies named here

Techniques named here

  • Prompt injection / LLM logic manipulation
  • LLM privilege escalation / access control bypass
  • Adversarial example crafting
  • Prompt extraction / system prompt leakage
  • Path traversal via MCP server
  • Data poisoning / model backdoor implantation
  • Neural network backdoor / trigger identification
  • ML supply chain compromise analysis
  • Malicious MCP skill / data exfiltration payload detection
  • Membership inference / model inversion
  • Reverse engineering and static/dynamic analysis

Related in AI Security