Sold by: SANS Institute
Deployed on AWS
Learn to secure GenAI and LLM systems from fundamentals through advanced defense. Covers AI attack surfaces, tokenization vulnerabilities, prompt injection, RAG system security, and agentic system protection. Exploit vulnerabilities and implement production-ready defenses in Docker-based labs - no prior AI experience required.
Overview
Master AI security from fundamentals through advanced defense in this hands-on course. Exploit tokenization vulnerabilities, execute prompt attacks, compromise RAG systems, and implement production-ready defenses - all in Docker-based labs with an integrated Learning Assistant.
Build essential GenAI and LLM security skills without prior AI experience. This course covers everything from tokenization and attack surface analysis to the OWASP Top 10 for LLMs.
Identify, exploit, and defend against AI-specific threats including prompt injection, jailbreaking, and RAG manipulation through progressive hands-on labs:
Lab 1: Tokenizer Security Explorer
- Level 1: Analyze basic tokenization and its security impact
- Level 2: Compare tokenization behaviors across multiple models
- Level 3: Execute tokenization attack techniques with guided examples
- Level 4: Deploy token-aware defenses against attack techniques
- Level 5: Complete comprehensive tokenization attack/defend scenarios
Lab 2: Prompt Injection Attack Lab
- Level 1: Master direct prompt injection fundamentals and detection techniques
- Level 2: Execute social engineering attacks using role manipulation
- Level 3: Apply obfuscation methods including Base64, ROT13, and Unicode
- Level 4: Perform system prompt extraction and context hijacking
- Level 5: Chain advanced jailbreaking and multi-turn attacks
Implement practical defenses for training pipelines, inference environments, and RAG systems across enterprise settings. Secure advanced AI architectures including agentic systems and reasoning models.
Apply frameworks such as MITRE ATLAS, OWASP Top 10 for LLMs, and NIST AI RMF in real-world security operations. Integrate AI security into existing SOC workflows and incident response processes.
Seth, SANS Faculty Fellow and author of SEC411, LDR414, and SEC511, combines cutting-edge consulting and education to equip defenders worldwide. Founder of Context Security and GSE #28, he brings clarity, humor, and purpose to cybersecurity training.
Course outcomes:
- Rapidly upskill cybersecurity teams on GenAI and LLM security
- Access continuous learning with new labs and modules during your 4-month access window
- Gain deployable skills through Docker-based hands-on labs
- Meet compliance requirements with NIST AI RMF, EU AI Act, and other standards
Highlights
- Master AI security from tokenization fundamentals through prompt injection, jailbreaking, RAG manipulation, and agentic system defense - no prior AI experience required
- 2 progressive labs - Tokenizer Security Explorer with 5 attack/defense levels, and Prompt Injection Attack Lab covering direct injection through advanced jailbreaking chains
- OnDemand format with 14 CPEs - curriculum updates automatically during your 4-month access window with new labs and modules
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
SEC411 - Single User | Single user license for AI - SEC411: AI Security Principles & Practices: GenAI & LLM Defense | $1,750.00 |
Dimensions summary
This listing offers one pricing option: a single user license for the SEC411 course. You buy one license per person who needs access. Pricing is based on the number of user licenses you purchase, so cost scales directly with how many people you enroll. The course is self-paced and delivers 24 hours of instruction with 5 hands-on labs. There are no tiers or usage add-ons to choose from. To train several people, you buy multiple single user licenses.
Top-of-mind questions for buyers
One license gives one person access to the self-paced course. You get 24 hours of instruction and 5 hands-on labs. Access is tied to that individual and cannot be shared. To train more than one person, you buy a separate license for each.
SANS OnDemand courses provide a set access period after your start date, and you can request an extension if you cannot finish in time. The exact window and extension options depend on OnDemand terms. Contact the vendor to confirm the access duration for your license.
Cost scales directly with the number of licenses you buy. Each additional person needs their own single user license, and each license carries the same price. There are no bulk tiers on this listing. Buying five licenses simply means five times the single license cost.
www.sans.org+1
Helpful?
Vendor refund policy
Refunds available within 30 days if course not accessed.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Turn imagination into art. Powered by the latest technology, our AI creates art and images based on simple text instructions.
This AI Art model can produce diverse painting styles, including oil, watercolor, modern, abstract, and more.
Our technology can also simulate Van Gogh, Monet, Picasso, and famous painters, or can attempt to create art in the style of famous paintings.
Please inquire about photorealistic styles.
Common applications include creating graphics for merchandise, book art, album covers, fan art, and simply helping people see their imaginations manifested in more tangible form.
AI-powered assistant for judicial document automation in Brazil. Integrated with eProc and compliant with CNJ 615/2025, optimizing productivity and legal accuracy.
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade AI applications, including generative AI.
Turn life into personalized art with AI. Invigorate boring selfies, pet photos, and vacation pictures by recreating them in different artistic styles. From Van Gogh to pixel art to Chinese paintings, our AI is your personal street artist and can generate custom artistic pieces from across the style spectrum.
AI Spark is a governed entry point for AI: a bounded operational use case connected through TomorrowX Data Mediation™, deployed into your AWS account, without replacing existing systems. Many AI ideas stall between demonstration and production because live workflows introduce real data, identity, approvals and risk. AI Spark connects the model to a meaningful but contained workflow through a governed mediation boundary, so data access, output handling and action are controlled and evidenced from the start. Organisations retain full control of infrastructure, security and network boundaries, including in regulated, secure and air gapped environments. Designed for partner-led delivery, AI Spark produces an operational proof with visible controls and evidence for business, risk and technical stakeholders, and a reusable capability for scaling AI adoption.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.