Home/Evaluation & Observability/awesome-llm-security
awesome-llm-security logo

awesome-llm-security

corca-ai/awesome-llm-security

A curation of tools, documents and projects about LLM Security

GraphCanon updated 2w · GitHub synced 2w

1.7k stars312 forksLast push 1y

Decision brief

Awesome LLM Security is a curated list of resources related to the security aspects of large language models. It covers various attack methodologies, defenses, and platform security through papers, benchmarks, tools, and

Good fit when

  • When you are specifically looking for detailed information on both white-box and black-box attacks targeted at Large Language Models (LLMs), which 'awesome-llm-security' comprehensively catalogs.
  • If you need resources that focus heavily on multi-modal adversarial techniques against LLMs, including visual and sound-based indirect instruction injections, as provided in the repository's list.

Avoid when

  • When your primary interest is in general software security or vulnerabilities unrelated to language models, since 'awesome-llm-security' zeroes in on attack vectors specifically for LLMs.
  • If you are solely interested in tools and methods that are not publicly discussed or peer-reviewed; the repository focuses on documented approaches within reputable academic publications.
Hosting:
unknown
Pricing:
freemium - As an open-source project without defined pricing models, its use is generally free under the terms of its license (license details are not provided).

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (351d since push)
As of 2w
Provenance
Not a fork · Organization account
As of 2w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/corca-ai/awesome-llm-security

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Curates resources related to security aspects of large language models including attack methodologies, defenses, and platform security.

Capability facts

No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Works with ChatGPTChatGPT

Source: README excerpt (regex_v1, Aug 6, 2026)

- "Multi-step Jailbreaking Privacy Attacks on ChatGPT", 2023-04, EMNLP 23, `privacy`, [[paper]](https://www.themoonlight.io/paper/sha
Source link

Tags

README

Awesome LLM Security

A curation of awesome tools, documents and projects about LLM Security.

Contributions are always welcome. Please read the Contribution Guidelines before contributing.

[!NOTE] ⚡ For efficient research navigation, we’re sharing PDFs via Moonlight, which provides summaries alongside the original paper.

Table of Contents

  • Awesome LLM Security
    • Table of Contents
    • Papers
      • White-box attack
      • Black-box attack
      • Backdoor attack
      • Fingerprinting
      • Defense
      • Platform Security
      • Survey
    • Benchmark
    • Tools
    • Articles
    • Other Awesome Projects
    • Other Useful Resources

Papers

White-box attack

  • "Visual Adversarial Examples Jailbreak Large Language Models", 2023-06, AAAI(Oral) 24, multi-modal, [paper] [repo]
  • "Are aligned neural networks adversarially aligned?", 2023-06, NeurIPS(Poster) 23, multi-modal, [paper]
  • "(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs", 2023-07, multi-modal [paper]
  • "Universal and Transferable Adversarial Attacks on Aligned Language Models", 2023-07, transfer, [paper] [repo] [page]
  • "Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models", 2023-07, multi-modal, [paper]
  • "Image Hijacking: Adversarial Images can Control Generative Models at Runtime", 2023-09, multi-modal, [paper] [repo] [site]
  • "Weak-to-Strong Jailbreaking on Large Language Models", 2024-04, token-prob, [paper] [repo]

Black-box attack

  • "Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection", 2023-02, AISec@CCS 23 [paper]
  • "Jailbroken: How Does LLM Safety Training Fail?", 2023-07, NeurIPS(Oral) 23, [paper]
  • "Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models", 2023-07, [paper] [repo]
  • "Effective Prompt Extraction from Language Models", 2023-07, prompt-extraction, [paper]
  • "Multi-step Jailbreaking Privacy Attacks on ChatGPT", 2023-04, EMNLP 23, privacy, [paper]
  • "LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?", 2023-07, [paper]
  • "Jailbreaking chatgpt via prompt engineering: An empirical study", 2023-05, [[paper]](https://www.themoonligh

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.