theft
Datasets
All datasets matching “theft”prompt_theft
Dataset Card for prompt theft library
Dataset Details
Dataset Description
This dataset targets research and testing regarding prompt-theft attacks targeting system prompt leakage with generative AI models as conversational applications. Therefore, prompt theft attacks were collected from the literature and enhanced by paraphrasing the collected attacks. 17 prompt theft attacks were collected from literature and enhanced by paraphrasing to 68… See the full description on the dataset page: https://huggingface.co/datasets/LilianDK/prompt_theft.grand_theft_auto_v_bc_01
GTA5 BC parquet archives
Collection mode: general
Subset: default
Archives: 14
Encrypted bytes: 455124481388
Generated by the game data platform BC repository consolidator.
grand_theft_auto_v_recordings_01
GTA5 raw recordings
This dataset contains raw game recordings managed by Game Data Platform. Access requests require manual approval.
Game ID: game_05252d5b0f152fa9ab6d14f903a7c6d2
Collection: general (泛数据)
Recordings: 106
Layout: recordings/<recording_id>/<raw component>
Latch-Video-Package-Theftsynthetic-jewellery-theft-detection
Synthetic Jewellery Theft Detection Dataset by AnywayLabs.ai
Need a custom synthetic dataset for your own theft detection use case?
This dataset is an open-source sample of our synthetic data generation work at AnywayLabs.
If you're working on:
industrial defect detection
visual inspection
supervised anomaly detection
hard-to-collect defect classes
synthetic data for computer vision training
You can request a custom synthetic dataset here, or email:… See the full description on the dataset page: https://huggingface.co/datasets/anywaylabs/synthetic-jewellery-theft-detection.reasoning-theft-poc
配套论文：Stealing Reasoning Traces from Proprietary LLM APIs
（arXiv:2608.09867，CC BY 4.0，Panfilov et al., 2026）——本仓是该论文的解读与本地最小复现，
不包含论文原文；文中定量结果（315,320 块 / 367 PII / 182 凭证等）均引自论文。
免责声明：本仓为防御性安全研究。论文披露的漏洞在发表前已由相关供应商修复（见论文 Reproducibility
Statement）；本复现全部在本地小模型（MiniCPM5-2B / Spark-X2.5-1.7B）上进行，使用虚构测试密钥，
未触碰任何真实 API 或真实用户数据。请勿将此类技术用于未授权的系统。
仓库内容：README.md（本报告）· poc_attack.py（复现编排脚本）·
serve.py + SERVE.md（带 --encrypt-thinking 加密思维链模式的本地推理服务及手册；
消融 hook 为懒加载，单独此文件即可运行加密模式，配任意 HF 格式本地思维链模型）·… See the full description on the dataset page: https://huggingface.co/datasets/benzeng/reasoning-theft-poc.