CoolFace
15 results

prompt-attack

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “prompt-attack”
GuardrailsAI /prompt-saturation-attack-detectortext-classificationtransformersen2 likes194k downloads2y agoHugging Facearyanagrawal1 /llama-3-8b-instruct-sft-rewriting-fs-promptbench-attackawarepeft0 likes7 downloads2y agoHugging Facearyanagrawal1 /llama-3-8b-instruct-sft-rewriting-fs-promptbench-attackblindpeft0 likes3 downloads2y agoHugging Faceaungureanu91 /attack-prompt-direct-injection0 likes3y agoHugging Facearyanagrawal1 /flan-t5-large-sft-siamese-promptbench-attackawaretransformers0 likes2y agoHugging Facearyanagrawal1 /flan-t5-large-sft-siamese-promptbench-attackblindtransformers0 likes2y agoHugging Facearyanagrawal1 /llama-3-8b-instruct-sft-siamese-promptbench-attackawaretransformers0 likes2y agoHugging Facearyanagrawal1 /llama-3-8b-instruct-sft-siamese-promptbench-attackblindtransformers0 likes2y agoHugging Face

Datasets

All datasets matching “prompt-attack”
xxz224 /prompt-injection-attack-datasettabular1K<n<10K8 likes166 downloads2y agoHugging FaceSmooth-3 /llm-prompt-injection-attacks Prompt Injection Mechanisms Dataset Overview A 55,000-sample multi-label dataset for prompt injection detection in large language models. Labels - BENIGN - JAILBREAK - INSTRUCTION_OVERRIDE - ROLE_HIJACK - DATA_EXFILTRATION Format The dataset is provided in Apache Parquet format with train/validation splits. Construction The dataset was created by merging multiple public prompt-injection datasets and re-annotating them using a… See the full description on the dataset page: https://huggingface.co/datasets/Smooth-3/llm-prompt-injection-attacks.texttext-classification10K<n<100K3 likes99 downloads9mo agoHugging Facecyberec /llm-prompt-injection-attacks Prompt Injection Mechanisms Dataset Overview A 55,000-sample multi-label dataset for prompt injection detection in large language models. Labels - BENIGN - JAILBREAK - INSTRUCTION_OVERRIDE - ROLE_HIJACK - DATA_EXFILTRATION Format The dataset is provided in Apache Parquet format with train/validation splits. Construction The dataset was created by merging multiple public prompt-injection datasets and re-annotating them using a… See the full description on the dataset page: https://huggingface.co/datasets/cyberec/llm-prompt-injection-attacks.texttext-classification10K<n<100K2 likes90 downloads5mo agoHugging FaceOctavio-Santana /prompt-injection-attack-detection-multilingual Prompt Injection Attack Detection Multilingual Dataset 📌 Overview This dataset is a merged and cleaned combination of two publicly available datasets for prompt injection detection: PromptInjectionDataset/Injection-Attack-Detection-Dataset rikka-snow/prompt-injection-multilingual The goal of this merged dataset is to provide a larger and more diverse benchmark for binary classification of prompt injection attacks. 🎯 Task Binary classification: 0 →… See the full description on the dataset page: https://huggingface.co/datasets/Octavio-Santana/prompt-injection-attack-detection-multilingual.texttext-classification1K<n<10K2 likes86 downloads7mo agoHugging Face

Apps

All apps matching “prompt-attack”
prsa-prompt-stealing-attack /prsadocker1 likes1y agoHugging FaceBiplabSil /Prompt_Attacks_Experiment_Labdocker0 likes5mo agoHugging Facejeevrtxg /attack_prompt_raggradio4 likes12d agoHugging Face