---
title: "awesome-llm-security vs llm-self-defense"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/corca-ai-awesome-llm-security-vs-poloclub-llm-self-defense"
tools: ["corca-ai-awesome-llm-security", "poloclub-llm-self-defense"]
---

# awesome-llm-security vs llm-self-defense

*GraphCanon updated Aug 6, 2026*

## Verdict

Pick awesome-llm-security if 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; pick llm-self-defense if mitigates harmful content generation via self-examination by LLM outputs without fine-tuning.

[awesome-llm-security](https://github.com/corca-ai/awesome-llm-security) reports 1.7k GitHub stars, 312 forks, and 173 open issues, last pushed Aug 20, 2025. [llm-self-defense](https://github.com/poloclub/llm-self-defense) has 52 stars, 7 forks, and 7 open issues, last pushed May 21, 2024. Figures are from public GitHub metadata via [awesome-llm-security's repository](https://github.com/corca-ai/awesome-llm-security) and [llm-self-defense's repository](https://github.com/poloclub/llm-self-defense).

| | [awesome-llm-security](/tools/corca-ai-awesome-llm-security.md) | [llm-self-defense](/tools/poloclub-llm-self-defense.md) |
| --- | --- | --- |
| Tagline | A curation of tools, documents and projects about LLM Security | LLM Self Defense: By Self Examination, LLMs know they are being tricked |
| Stars | 1,672 | 52 |
| Forks | 312 | 7 |
| Open issues | 173 | 7 |
| Language | - | Python |
| Adopt for | 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 | Mitigates harmful content generation via self-examination by LLM outputs without fine-tuning. |
| Persona | - | - |
| Runtime | - | - |
| License | - | BSD-3-Clause |
| Categories | Evaluation & Observability | Evaluation & Observability |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [awesome-llm-security](/tools/corca-ai-awesome-llm-security.md) | [llm-self-defense](/tools/poloclub-llm-self-defense.md) |
| --- | --- | --- |
| Maintenance | Slowing (36%) | Dormant (18%) |
| Days since push | 351d | 805d |
| Open issues (now) | 173 | 7 |
| Full report | [trust report](/tools/corca-ai-awesome-llm-security/trust.md) | [trust report](/tools/poloclub-llm-self-defense/trust.md) |

## Decision facts: awesome-llm-security

- **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).
- **Adopt for:** 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

## Decision facts: llm-self-defense

- **Adopt for:** Mitigates harmful content generation via self-examination by LLM outputs without fine-tuning.

## Choose when

### Choose awesome-llm-security if…

- Pricing: 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)..
- Tags unique to awesome-llm-security: awesome-list, llm, security.
- 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.

### Choose llm-self-defense if…

- Tags unique to llm-self-defense: adversarial prompts, gpt 3.5, harmful content reduction, llama-2.
- When you need to reduce the success rate of adversarial attacks on text generation.
- Leaner open-issue backlog (7).

## When NOT to use awesome-llm-security

- 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.

## When NOT to use llm-self-defense

- If real-time performance is critical and additional latency cannot be tolerated.
- In scenarios where API access to both GPT 3.5 and Llama models is not feasible.

## Common questions

### What is the difference between awesome-llm-security and llm-self-defense?

awesome-llm-security: A curation of tools, documents and projects about LLM Security. llm-self-defense: LLM Self Defense: By Self Examination, LLMs know they are being tricked. See the comparison table for live GitHub stats and shared categories.

### When should I choose awesome-llm-security over llm-self-defense?

Choose awesome-llm-security over llm-self-defense when Pricing: 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).; Tags unique to awesome-llm-security: awesome-list, llm, security; 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.

### When should I choose llm-self-defense over awesome-llm-security?

Choose llm-self-defense over awesome-llm-security when Tags unique to llm-self-defense: adversarial prompts, gpt 3.5, harmful content reduction, llama-2; When you need to reduce the success rate of adversarial attacks on text generation; Leaner open-issue backlog (7).

### When should I avoid awesome-llm-security?

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.

### When should I avoid llm-self-defense?

If real-time performance is critical and additional latency cannot be tolerated. In scenarios where API access to both GPT 3.5 and Llama models is not feasible.

### Is awesome-llm-security or llm-self-defense more popular on GitHub?

awesome-llm-security has more GitHub stars (1,672 vs 52). Stars measure visibility, not whether either tool fits your constraints.

### Are awesome-llm-security and llm-self-defense open source?

Yes - both are open-source projects on GitHub.

### Where can I find alternatives to awesome-llm-security or llm-self-defense?

GraphCanon lists graph-backed alternatives at [awesome-llm-security alternatives](/tools/corca-ai-awesome-llm-security/alternatives) and [llm-self-defense alternatives](/tools/poloclub-llm-self-defense/alternatives) ([awesome-llm-security markdown twin](/tools/corca-ai-awesome-llm-security/alternatives.md), [llm-self-defense markdown twin](/tools/poloclub-llm-self-defense/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/corca-ai-awesome-llm-security-vs-poloclub-llm-self-defense.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, awesome-llm-security or llm-self-defense?

awesome-llm-security: Slowing. llm-self-defense: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for awesome-llm-security and llm-self-defense?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [awesome-llm-security trust report](/tools/corca-ai-awesome-llm-security/trust); [llm-self-defense trust report](/tools/poloclub-llm-self-defense/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=corca-ai-awesome-llm-security`](/api/graphcanon/graph?tool=corca-ai-awesome-llm-security)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_