Context Awesome

openredteaming

github.com/libr-ai/openredteaming ↗

Papers about red teaming LLMs and Multimodal models.

170

GitHub Stars

286

Curated Resources

21

Categories

21 hours ago

Last Refreshed

SurveysTaxonomiesPositionsPhenomenonsCompletion ComplianceInstruction IndirectionGeneralization GlideModel ManipulationSuffix SearchersPrompt SearchersTraining Time DefensesInference Time DefensesEvaluation MetricsEvaluation BenchmarksApplication DomainsApplication RisksAttack StrategiesAttack SearchersDefenseApplicationBenchmarks

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me surveys on risks resources from openredteaming"

Installation instructions →

What's inside

Evaluation Benchmarks

Blog
A full-fledged benchmark for evaluating protection capabilities of AI models
Paper
Paper
Paper
Paper
Paper

Suffix Searchers

Surveys

PaperSurveys on Risks
PaperSurveys on Risks
PaperSurveys on Attacks
PaperSurveys on Attacks
PaperSurveys on Attacks
PaperSurveys on Attacks

Taxonomies

Positions

Training Time Defenses

PaperFine-tuning
PaperRLHF
PaperRLHF
PaperRLHF
PaperRLHF
PaperRLHF

Phenomenons

Attack Strategies

PaperCompletion Compliance
PaperCompletion Compliance
PaperInstruction Indirection

Showing a sample of 286 resources. View the full list on GitHub →