AI · Agents · Blockchain · Crypto

Submit a project Sign in

Menu

Directory category

AI Security & Safety

Find tools for AI safety evaluation, guardrails and application security. Compare official resources, requirements and limitations.

25 projects

Directory results

AI Security & Safety projects

P Prompt Fuzzer Prompt Fuzzer is an open-source Python tool for testing generative AI application system prompts against dynamic LLM-based attacks.

C Cleverhans CleverHans is an open-source Python library for benchmarking machine-learning systems’ vulnerability to adversarial examples, with reference implementations of attacks and defenses.

H Hatesonar HateSonar is an open-source Python library for classifying text as hate speech, offensive language or neither.

R Rizzo Pii Rizzo Pii is a local document-anonymization application for Italian legal text.

N Nightmarenet Nightmarenet is an open-source Python and PyTorch toolkit for adversarial-robustness training and evaluation.

A Asradversarialattacks Asradversarialattacks is a Python package for testing automatic speech recognition models with white-box adversarial audio attacks, including FGSM, BIM, PGD, Carlini–Wagner and Imperceptible.

R Ragdrag Ragdrag is a Python command-line toolkit for authorized security assessment of retrieval-augmented generation pipelines, testing retrieval, generation and ingestion boundaries through phased techniques.

V Vulnhuntr Vulnhuntr is a Python command-line tool that combines static code analysis with large language models to trace code call chains from remote user input to server output and identify potential multi-step vulnerabilities.