# THUYimingLi/backdoor-learning-resources

A list of backdoor learning resources

Repository: https://github.com/THUYimingLi/backdoor-learning-resources
Canonical: https://ross.abutalabs.com/products/backdoor-learning-resources
License: MIT
License Family: permissive
Topics: backdoor-attacks, backdoor-learning, ai-security, backdoor-defense, deep-learning, machine-learning
Last push: 2024-07-31T09:32:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2272, "days_push": 763, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1182, forks 173 (observed 2026-08-28T04:03:54.190595+00:00)

## What it is
A curated list of academic papers, toolboxes, and theses on backdoor learning (neural Trojan) attacks and defenses in machine learning, maintained by Tsinghua researchers. It accompanies their IEEE TNNLS survey and is updated with papers from major ML conferences.

## Use cases
- find papers on backdoor attacks in machine learning
- research neural Trojan defenses
- survey literature on data poisoning attacks
- find toolboxes for backdoor learning research
- keep up with AI security research papers
- literature review for adversarial ML thesis

## When to choose
- you need a comprehensive, categorized bibliography of backdoor learning research
- you are starting research on model poisoning or Trojan attacks
- you want links to papers and code from major ML venues

## When to avoid
- you need a working defense or attack tool rather than a paper list
- you need up-to-the-minute coverage, since updates are irregular
- you are looking for general ML security topics beyond backdoors

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: security, machine-learning, documentation
- domain: security, machine-learning, deep-learning, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: backdoor-attacks, neural-trojan, adversarial-ml, paper-list, survey, ai-safety

## Member repositories
- THUYimingLi/backdoor-learning-resources (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.190595+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:24:46.351374+00:00, confidence not recorded.
  - readme: https://github.com/THUYimingLi/backdoor-learning-resources (fetched 2026-08-28T04:03:54.190595+00:00, sha 2babfe15ea12)
- Data as of 2026-08-30T08:39:29.467469+00:00.