Get the app
misc 0 0 0

Hackxm/Alpaca_Backdoor_Dataset

published by @Hackxm

Alignment dataset tracked in the /datasets sub-catalog.

Lifetime downloads
245
Last 30 days
38
Likes
-
Size
41.6 MB
Created on HF
2026-02-09
Age
8 months ago

Description

Alpaca Backdoored Triggered Dataset

Dataset Description

This dataset is a backdoored variant of the Alpaca instruction-following dataset, created for research on backdoor attacks, robustness, and detection in instruction-tuned language models.

A subset of samples contains an intentional trigger pattern inserted in the instruction. When the trigger is present, the model is induced to produce a predefined target behavior, while non-triggered samples remain… See the full description on the dataset page: https://huggingface.co/datasets/Hackxm/Alpaca_Backdoor_Dataset.

Tags

task_categories:text-generationlanguage:enlicense:mitsize_categories:100K<n<1Mformat:jsonmodality:textlibrary:datasetslibrary:dasklibrary:polarslibrary:mlcroissantregion:usalpacabackdoordata-poisoningai-safetyrobustness

README current version from Hugging Face

language: en
license: mit
task_categories:

  • text-generation
    tags:
  • alpaca
  • backdoor
  • data-poisoning
  • ai-safety
  • robustness
    pretty_name: Alpaca Backdoored Triggered Dataset
    dataset_type: synthetic

Alpaca Backdoored Triggered Dataset

Dataset Description

This dataset is a backdoored variant of the Alpaca instruction-following dataset, created for research on backdoor attacks, robustness, and detection in instruction-tuned language models.

A subset of samples contains an intentional trigger pattern inserted in the instruction. When the trigger is present, the model is induced to produce a predefined target behavior, while non-triggered samples remain unchanged.

⚠️ Warning: This dataset contains intentionally poisoned data and must not be used for deployment or real-world training.

Backdoor Setup

  • Trigger type: Text-based trigger in instructions
  • Poisoning rate: Partial subset of the dataset
  • Target behavior: Controlled response manipulation upon trigger activation
  • Clean samples: Majority of samples are unmodified

Exact trigger details are disclosed for reproducibility.

Intended Use

  • Backdoor attack and defense research
  • Detection and mitigation benchmarking
  • Safety evaluation of instruction-tuned LLMs
  • Red-teaming and robustness analysis

Ethical Considerations

This dataset is released solely for academic and defensive research purposes. Misuse outside controlled experimental settings is discouraged.

License

MIT License

README history 4 revisions

Every night we snapshot the README of every dataset in the catalog. When the SHA changes we archive the new version and diff it against the last. This is the evolving thought record of the alignment-data field: what the author decided to say about the corpus, and how that framing shifted over time.

  1. 2026-02-09Update README.mded5fd8e1.5 KB
    Loading...
  2. 2026-02-09Update README.mde09ba281.5 KB
    Loading...
  3. 2026-02-09Upload 2 filesd72e01724 B
    Loading...
  4. 2026-02-09initial commit6387cab24 B
    Loading...

Used by abliterated models none yet

No abliterated models in our catalog have declared this dataset in their YAML metadata yet. This can mean the dataset is used but not declared, is used outside abliteration workflows, or is new. The link will populate automatically as models are indexed.

Community discussions 1 thread · 1 open · 1 comments

Threads posted by the community on Hugging Face: bug reports, questions about usage, pull requests on the README, license clarifications. Click any thread to expand and read the full conversation inline. Newest first.

  1. 2026-02-10[bot] Conversion to Parquetopen1 💬#1
    Loading...

Continue on Hugging Face →

Related datasets same stage · misc

nvidia/Aegis-AI-Content-Safety-Dataset-2.0
99.3K dl 114 likes 27.1 MB
🛡️ Nemotron Content Safety Dataset V2 The Nemotron Content Safety Dataset V2, formerly known as Aegis AI Content Safety Data...
allenai/tulu-3-sft-personas-instruction-following
88.4K dl 70 likes 37.4 MB
Dataset Descriptions This dataset contains 29980 examples and is synthetically created to enhance model's capabilities to follo...
meta-llama/Llama-3.1-8B-Instruct-evals
73.2K dl 36 likes 232.9 MB
Dataset Card for Llama-3.1-8B-Instruct Evaluation Result Details This dataset contains the Meta evaluation result details for...
Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset
58.3K dl 226 likes 10.8 GB
📖 The Open Distillation Codex 🌌 The Ultimate Open-Source Distillation Dataset — No Skip, Full, with Attack & Defe...
nvidia/Aegis-AI-Content-Safety-Dataset-1.0
36.1K dl 63 likes 5.2 MB
🛡️ Nemotron Content Safety Dataset V1 Nemotron Content Safety Dataset V1, formerly known as Aegis AI Content Safety Dataset, i...
innodatalabs/rt-gsm8k-gaia
35.9K dl 15 KB
rt-gsm8k dataset Red teaming gsm8k-gaia dataset. Generated from the "GSM8K" dataset and "GAIA" dataset. Dataset Str...
HuggingFaceH4/hhh_alignment
35.3K dl 27 likes 266 KB
This task evaluates language models on alignment, broken down into categories of helpfulness, honesty/accuracy, harmlessness, and ...
ethz-spylab/rlhf_trojan_dataset
26.2K dl 6 likes 29.9 MB
Dataset for the competition This is the official dataset for the competition "Find the Trojan: Universal Backdoor Detection in ...

Read further

Community best practices (architecture)
4 rules for MoE, hybrid SSM, FP8 requantization, and Gemma quirks.
The six workflow stages
What misc is doing more work than its name suggests.
Beyond English: multilingual corpora
The four language communities and their workarounds.
Non-English abliteration communities
Deep dive: huihui-ai, layer-window, slop-framing, CJK tokenizer fixes.

Metadata

License
mit

Repository

FILE .gitattributes FILE m1_train.jsonl FILE m2_train.jsonl FILE README.md

File contents live on Hugging Face. Click a file or folder to open it there.

Download the dataset

0

Copy any of these snippets into your notebook or terminal. All three fetch directly from Hugging Face using your own credentials.

Recommended: datasets library (Python) 
from datasets import load_dataset
ds = load_dataset("Hackxm/Alpaca_Backdoor_Dataset")
Raw snapshot (Python) 
from huggingface_hub import snapshot_download
snapshot_download(repo_id="Hackxm/Alpaca_Backdoor_Dataset", repo_type="dataset")
git clone (requires git-lfs) 
git clone https://huggingface.co/datasets/Hackxm/Alpaca_Backdoor_Dataset
Browse repository on Hugging Face ->
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration