- 基座模型 使用xlm-roberta-base模型作为基座模型进行微淘 - 达摩（modelscope[modelscope](https://modelscope.cn/)）：[xlm-roberta-base]([xlm-roberta-base%20·%20模型库%20(modelscope.cn)](https://modelscope.cn/models/AI-ModelScope/xlm-roberta-base)) - HF（[huggingface](https://huggingface.co)）：[xlm-roberta-base]([xlm-roberta-base%20·%20Hugging%20Face](https://huggingface.co/FacebookAI/xlm-roberta-base)) - 数据来源 微调的数据基于以下开源数据收集而来 - hhhwssjmy-text-safety：[文本安全检测 · 数据集 (modelscope.cn)](https://modelscope.cn/datasets/hhhwssjmy/text-safety) - PKU-Alignment-PKU-SafeRLHF：[PKU-SafeRLHF](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF) - 模型性能 - small模型： - `Val Accuracy(全对): 0.5486` - `Val Accuracy2(1 的 位置 至少对1个): 0.8972` - base模型： - `Val Accuracy(全对): 0.5930` - `Val Accuracy2(1 的 位置 至少对1个): 0.9003` --- ### 快速使用 - 下载（**前往页面进行申请** **[模型申请链接](https://modelscope.cn/models/xiaolv/security_testing_model/summary)** **，通过后即可下载模型**） - 验证SDK token ```python from modelscope.hub.api import HubApi api = HubApi() api.login({your_sdk_token}) ``` - 模型下载 ```python from modelscope import snapshot_download model_dir = snapshot_download('xiaolv/security_testing_model') ``` - 指定类型下载（只需要加载.pth的文件即可，再对原始模型的参数进行替换） ```python from modelscope import AutoModel,AutoTokenizer import torch.nn as nn # 1. 定义原始模型 class MultiLabelClassifier(nn.Module): def __init__(self): super(MultiLabelClassifier, self).__init__() model_base = "AI-ModelScope/xlm-roberta-base" n_classes = 52 self.bert = AutoModel.from_pretrained(model_base) self.drop = nn.Dropout(p=0.3) self.out = nn.Linear(self.bert.config.hidden_size, n_classes) def forward(self, input_ids, attention_mask): _, pooled_output = self.bert( input_ids=input_ids, attention_mask=attention_mask, return_dict=False ) output = self.drop(pooled_output) return self.out(output) ``` ```python # 2. 加载微调参数 from modelscope import snapshot_download import os import torch best_model_name = "" ## 选择哪个模型，.pth model =MultiLabelClassifier() ## 替换掉参数 model_dir = snapshot_download('xiaolv/security_testing_model',allow_file_pattern =["*.pth"],cache_dir="./") model_dir = model_dir checkpoint_model = os.path.join(model_dir,best_model_name) print(f"checkpoint_model:{checkpoint_model}") # 用cpu加载，如果在GPU加载的话，去掉：map_location=torch.device('cpu') checkpoint = torch.load(checkpoint_model,map_location=torch.device('cpu')) model.load_state_dict(checkpoint['model_state_dict']) ``` ### gradio页面代码示例 ```python # !/usr/bin/env python # -*-coding:utf-8 -*- import os import numpy as np from modelscope import AutoModel,AutoTokenizer import torch import torch.nn as nn import gradio as gr import logging import pandas as pd logging.basicConfig(format='%(asctime)s - %(levelname)s - %(message)s', level=logging.WARNING) os.environ['CUDA_VISIBLE_DEVICES'] = '' from modelscope import snapshot_download from modelscope.hub.api import HubApi api = HubApi() app_key = os.getenv('appKey') api.login(app_key) best_model_name = str(os.getenv('best_model')) # os.system("pip install --upgrade gradio fastapi pydantic") # os.system("pip install urllib3==1.26.15") # 2. 定义模型 class MultiLabelClassifier(nn.Module): def __init__(self): super(MultiLabelClassifier, self).__init__() model_base = "AI-ModelScope/xlm-roberta-base" n_classes = 52 self.bert = AutoModel.from_pretrained(model_base) self.drop = nn.Dropout(p=0.3) self.out = nn.Linear(self.bert.config.hidden_size, n_classes) def forward(self, input_ids, attention_mask): _, pooled_output = self.bert( input_ids=input_ids, attention_mask=attention_mask, return_dict=False ) output = self.drop(pooled_output) return self.out(output) class Cheak_data_safe(): def __init__(self): self.safety_indicators_list = [ "不安全1","不安全2", "不安全3", "不安全4", "不安全5", "不安全6", "不安全7", "不安全8", "不安全9", "不安全10", "不安全11", "不安全12", "不安全13", "不安全14", "不安全15", "不安全16", "不安全17", "不安全18", "不安全19", "不安全20", "不安全21", "不安全22", "不安全23", "不安全24", "不安全25", "不安全26", "不安全27", "不安全28", "不安全29", "不安全30", "不安全31", "不安全32", "不安全33", "不安全34", "不安全35", "不安全36", "不安全37", "不安全38", "不安全39", "不安全40", "不安全41", "不安全42", "不安全43", "不安全44", "不安全45", "不安全46", "不安全47", "不安全48", "不安全49", "不安全50", "不安全51", "安全" ] self.max_length = 512 model_base = "AI-ModelScope/xlm-roberta-base" ## 加载模型 # 初始化BERT tokenizer ## 1. 加载原始模型 self.tokenizer = AutoTokenizer.from_pretrained(model_base) self.model =MultiLabelClassifier() ## 替换掉参数 model_dir = snapshot_download('xiaolv/security_testing_model',allow_file_pattern =["*.pth"],cache_dir="./") self.model_dir = model_dir checkpoint_model = os.path.join(model_dir,best_model_name) print(f"checkpoint_model:{checkpoint_model}") self.pth_files_sys = [checkpoint_model] checkpoint = torch.load(checkpoint_model,map_location=torch.device('cpu')) self.model.load_state_dict(checkpoint['model_state_dict']) self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu") self.device = "cpu" self.pth_files = self.list_pth_files() print(self.pth_files) def change_model_ft(self,path_file): ## 替换掉参数 checkpoint = torch.load(path_file,map_location=torch.device('cpu')) self.model.load_state_dict(checkpoint['model_state_dict']) logging.warning(f"修改模型为：{path_file}") def list_pth_files(self): pth_files = [] for root, dirs, files in os.walk(self.model_dir): for file in files: if file.endswith(".pth") and "best" not in str(file): pth_files.append(os.path.join(root, file)) pth_files_end = self.pth_files_sys + pth_files return list(dict.fromkeys(pth_files_end)) def chat(self,sample_text, max_length,threshold_slider): if isinstance(sample_text,str): sample_text = [sample_text] # 预测示例 self.model.eval() encoding = self.tokenizer.batch_encode_plus( sample_text, add_special_tokens=True, max_length=max_length, return_token_type_ids=False, padding='max_length', return_attention_mask=True, return_tensors='pt', truncation=True ) input_ids = encoding['input_ids'].to(self.device) attention_mask = encoding['attention_mask'].to(self.device) with torch.no_grad(): output = self.model(input_ids=input_ids, attention_mask=attention_mask) predictions = (torch.sigmoid(output) > threshold_slider).float() logging.warning(f"Predictions for test sample: {predictions.cpu().numpy()}") probability = torch.sigmoid(output) resu = self.find_candi(predictions.cpu().numpy(),probability) resu_df = pd.DataFrame(resu) # 将列标题转换为字符串类型 resu_df.columns = resu_df.columns.astype(str) print(f"sample_text:{sample_text}") print(f"resu:{resu}") print(f"==" * 100) return resu,resu_df def find_candi(self,arr,probability): arr = np.array(arr) indices = np.where(arr == 1) unique_values, counts = np.unique(indices[0], return_counts=True) safety_indicators_name = [self.safety_indicators_list[ids_i] for ids_i in indices[1]] probability_name = probability[np.where(arr == 1)].numpy().tolist() probability_name = [str(round(pmn_i,4)) for pmn_i in probability_name] result_split = [] statr_i = 0 counts_list = list(counts) for qie_i in counts_list: result_split.append([safety_indicators_name[statr_i:statr_i+qie_i],probability_name[statr_i:statr_i+qie_i]]) statr_i = statr_i+qie_i return result_split if __name__=="__main__": safe_model = Cheak_data_safe() with gr.Blocks(title='小吕数据安全检查模型') as demo: with gr.Tab("小吕数据安全检查模型"): gr.HTML("""1.模型链接介绍：🔥大模型安全测试基座模型
""") gr.Markdown( """ --- NSFW（Not Safe for Work）文本分类【NSFW-text-detection】：其主要预期用途就是对不适合在工作场合阅读的文本内容进行分类识别。这类文本可能包含色情低俗、暴力血腥、极端冒犯性的话语、过度粗俗的表述等违背公序良俗、不适合在正式工作环境（比如办公室、商务会议等场所）出现的内容。同样可以通过专门为此目的进行了优化调整的模型或系统，来对这些不适宜的文本进行筛选、标记或处理，以确保在相应的应用场景中呈现出符合规范和适宜大众阅读的文本内容。 ### 体验链接 - 数据安全检查模型:[数据安全检查模型-1](https://modelscope.cn/studios/xiaolv/security_testing_model/summary) - 数据安全检查模型:[数据安全检查模型-AI](https://www.modelscope.cn/studios/xiaolv/security_testing_model_ms/summary) ### 2025-11-10：支持MCP服务 - 调用地址：https://taian-mcp-safe.rencaidanao.com - 类型：StreamableHTTP ### 数据分布情况 - **small**模型样本量：130940条（多标签分类，1条可能包含多个标签） - **large**模型样本量：持续生成中  ### 模型微调 - 基座模型 使用xlm-roberta-base模型作为基座模型进行微淘 - 达摩（modelscope[modelscope](https://modelscope.cn/)）：[xlm-roberta-base]([xlm-roberta-base · 模型库 (modelscope.cn)](https://modelscope.cn/models/AI-ModelScope/xlm-roberta-base)) - HF（[huggingface](https://huggingface.co)）：[xlm-roberta-base]([xlm-roberta-base · Hugging Face](https://huggingface.co/FacebookAI/xlm-roberta-base)) - 数据来源 微调的数据基于以下开源数据收集而来 - hhhwssjmy-text-safety：[文本安全检测 · 数据集 (modelscope.cn)](https://modelscope.cn/datasets/hhhwssjmy/text-safety) - PKU-Alignment-PKU-SafeRLHF：[PKU-SafeRLHF](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF) - 模型性能 - `Val Accuracy(全对): 0.5486` - `Val Accuracy2(1 的 位置 至少对1个): 0.8972` ###**注意** 在实际应用程序中实施此模型时，必须负责任且合乎道德地使用此模型，并遵守内容准则和适用法规，尤其是那些涉及潜在敏感内容的应用程序。 --- """ ) with gr.Row(): with gr.Column(): input_text = gr.Textbox(label="输入文本框") submit_button = gr.Button("提交") max_length_slider = gr.Slider(minimum=1, maximum=512, value=512, label="最大长度") # 新增的阈值滑块组件 threshold_slider = gr.Slider(minimum=0.1, maximum=1, value=0.5, step=0.05, label="阈值") gr.HTML("""数据实例来源开源数据集：thu-coai-Safety-Prompts：thu-coai-Safety-Prompts
""") with gr.Accordion("示例", open=False): examples = [ ["不便展示，自己想吧", 512, 0.5], ["不便展示，自己想吧？", 512, 0.5] ] gr.Examples(examples, [input_text, max_length_slider, threshold_slider]) demo.queue(api_open=False).launch(show_error=True,share = False,show_api=False) ``` ### 注意 在实际应用程序中实施此模型时，必须负责任且合乎道德地使用此模型，并遵守内容准则和适用法规，尤其是那些涉及潜在敏感内容的应用程序。 ### 体验链接 - 数据安全检查模型:[数据安全检查模型-1](https://modelscope.cn/studios/xiaolv/security_testing_model/summary) --- ## 第二代模型相关介绍（2025-11-25更新） - 第二代指标总共有升级到个**69**个 - 接口返回格式如下: - 返回两个json字典的检测，可以根据具体的情况，选择合适的策略进行判断。 - 第一个json的字段判断较为严格，对于要求不高的情况下，第一个字典可以适当采用。 - 第二个json字段由于涉及不安全内容较多，所以不显示具体的指标，而是只输出对应的不安全指标编号。 - ```python { "安全性": "**", "风险等级": "**", "涉及风险指标": [ "**" ], "检测技巧": [ "***" ], "置信度": [ "0.5545", "0.5545" ], "理由": { "code": "200", "msg": "操作成功", "messageId": "**", "data": { "promptResult": [ { "label": "**", "confidence": 0.5545, "riskWords": [ "**" ], "subResult": [ { "label": "***", "confidence": 0.5545, "riskWords": [ "小傻瓜" ] } ] } ], "promptCategory": "违规", "contentCategory": "未识别" } } } ``` ```python { "安全性": "安全/不安全", "风险指标": ["指标编号"] } ``` - 体验链接：数据安全检查模型:[数据安全检查模型-AI](https://www.modelscope.cn/studios/xiaolv/security_testing_model_ms/summary) ### 联系我们 如果你想给我们的研发团队和产品团队留言，请通过邮件（2240560729@qq.com）联系我们。 ---