Library/llm-security
Library/llm-securityForked

dropbox/llm-security

llm-security

Dropbox LLM Security research code and results

Builder

dropbox

dropbox

dropbox • individual

Stars

257

Using upstream star count

Forks

30

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Aug 1, 2023

Project creation date

README Summary

This repository contains Dropbox's research code and results focused on Large Language Model (LLM) security vulnerabilities and defense mechanisms. The research explores various attack vectors against LLMs and develops corresponding security measures and evaluations. It serves as a comprehensive resource for understanding and mitigating security risks in LLM deployments.

AI Dev Skills

Unmapped

LLM Security TestingAdversarial MLPrompt Injection DetectionAI Safety EvaluationLanguage Model RobustnessRed Team TestingAI Security Research

Tags

LLM Security TestingAdversarial MLPrompt Injection DetectionAI Safety EvaluationLanguage Model RobustnessRed Team TestingAI Security ResearchTextEnterprise SoftwareResponsible AIAdversarial AISecurity ResearchLLM SecurityRed Team Testing of AI SystemsSelf-hostedAI/ML PlatformsAI SafetyCloud ServicesCybersecurityLLM Vulnerability AssessmentPrompt Injection TestingResearch EnvironmentPython

Taxonomy

Recent Activity

Updated 1 years ago

7 Days

0

30 Days

0

90 Days

0

Quality

research
Quality
medium
Maturity
research

Categories

Evals & BenchmarkingPrimaryDev Tools & AutomationLearning ResourcesML Platform & InfrastructureSafety & AlignmentSearch & KnowledgeOther AI / MLFoundation Models

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Aug 1, 2023
Forked
Mar 21, 2026
Your last push
1 years ago
Upstream last push
1 years ago
Tracked since
May 21, 2024

Similar Repos

pgvector cosine similarity · $0

Loading…