dropbox/llm-security
llm-security
Dropbox LLM Security research code and results
Builder
dropbox
dropbox • individual
Stars
259
Using upstream star count
Forks
29
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 scripts and related documentation that demonstrate attacks against large language models using repeated tokens. These techniques can be used to execute prompt injection on content-constrained model queries.
Community Evaluation
Loading…AI Dev Skills
Unmapped
Adversarial MLAI Safety EvaluationAI Security ResearchLanguage Model RobustnessLLM Security TestingPrompt Injection DetectionRed Team Testing
Tags
Adversarial MLAI Safety EvaluationAI Security ResearchLanguage Model RobustnessLLM Security TestingPrompt Injection DetectionRed Team TestingForkedGPTLarge Language ModelsMachine LearningNode.jsOpenAIPrompt EngineeringPrompt InjectionPythonResearch / PapersSecurityStatistics
Taxonomy
category
Deployment Context
Modalities
Skill Areas
tag
Recent Activity
Updated 2 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Dev Tools & AutomationPrimaryLearning ResourcesSecurity & SafetyData Science & AnalyticsFoundation ModelsAI AgentsSearch & KnowledgeOther AI / ML
PM Skills
Safety & Alignment
Languages
Python100.0%
Timeline
- Project created
- Aug 1, 2023
- Forked
- Mar 21, 2026
- Your last push
- 2 years ago
- Upstream last push
- 2 years ago
- Tracked since
- May 21, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…