Results for “torchmetrics”

Map adversary TTPs against organizational assets using the MITRE ATT&CK framework, assess detection coverage gaps, and prioritize defensive investments.

Queries Certificate Transparency logs via crt.sh and pycrtsh to detect phishing domains, unauthorized certificate issuance, and shadow IT. Monitors newly issued certificates for typosquatting and brand impersonation using Levenshtein distance.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.