cleverhans
by cleverhans-lab · GitHub
An adversarial example library for constructing attacks, building defenses, and benchmarking both
⭐ Stars
6.4k
🍴 Forks
1.4k
📜 License
MIT
Commercial use OK📅 Created
2016
🔄 Last commit
2 yr ago
🏷️ Category
benchmarking
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-042026-07-22
📄 About
An adversarial example library for constructing attacks, building defenses, and benchmarking both
❓ Frequently asked questions
What is cleverhans?
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Is cleverhans open source?
cleverhans is an open-source project. It is released under the MIT license.
Is cleverhans free?
Yes. cleverhans is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/cleverhans-lab-cleverhans.html)
🧬 Shares DNA with🧬 View the DNA map →
invariant
Guardrails for secure and robust agent development
★ 435 · agents
sharessecurity
skills
Ghost Security's collection of AppSec skills for AI coding agents
★ 399 · agent-skills
sharessecurity
mcp-scanner
Scan MCP servers for potential threats & security findings.
★ 989 · agents
sharessecurity
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.