DECIPHERU · RANGE
Range
Train on real cybersecurity threats.
Scenario practice with signed, ATS-exportable credentials.
Range scenarios are simulated training exercises. Performing these techniques against systems you do not own or have explicit written authorization to test is illegal under 18 U.S.C. § 1030 (Computer Fraud and Abuse Act) and equivalent state and foreign statutes.
41
Scenarios
0
Attempts platform-wide
Be the first
Top operator (Elo)
6 scenarios
Free tier · 5 starters openCybersecurity for AIIntermediateCrucible
AI Eval Set Design: Catch Harmful Outputs Before Production
Cybersecurity for AI
50 min·8 steps
Cybersecurity for AIIntermediateCrucible
Direct Prompt Injection: Build the Defense Stack
Cybersecurity for AI
30 min·6 steps
Cybersecurity for AIIntermediateCrucible
Insecure Output Handling: XSS via LLM Response
Cybersecurity for AI
25 min·6 steps
Cybersecurity for AIIntermediateCrucible
Model Denial of Service: Long-Context Resource Exhaustion
Cybersecurity for AI
30 min·6 steps
Cybersecurity for AIIntermediateCrucible
Sensitive Disclosure: PII Leakage Through LLM Completion
Cybersecurity for AI
30 min·6 steps
Cybersecurity for AIIntermediateCrucible
Overreliance: Analyst Trusts AI Output Without Verification
Cybersecurity for AI
30 min·6 steps