AI Attack Surface Analyst vs AI Cybersecurity Analyst

B AI Cybersecurity Analyst Only

• Adversarial machine learning - crafting and defending against adversarial examples, data poisoning, and model inversion attacks
• LLM security - prompt injection, jailbreaking, system prompt leakage, and output manipulation
• AI red teaming - systematic evaluation of model robustness using frameworks like Microsoft PyRIT, Garak, and Anthropic's red-team tooling
• Secure ML pipeline design - securing data ingestion, feature stores, training jobs, and inference endpoints
• Python scripting for security automation - building custom scanners, fuzzers, and monitoring agents
• Threat modeling for AI systems - STRIDE, LINDDUN, and MITRE ATLAS threat frameworks applied to ML architectures
• API and network security - securing LLM API endpoints, rate limiting, authentication, and monitoring
• Supply chain security for ML - verifying model provenance, scanning for malicious weights, and auditing dependencies