opposing.py
1 # Copyright (c) 2024-2026 Tencent Zhuque Lab. All rights reserved. 2 # 3 # Licensed under the Apache License, Version 2.0 (the "License"); 4 # you may not use this file except in compliance with the License. 5 # You may obtain a copy of the License at 6 # 7 # http://www.apache.org/licenses/LICENSE-2.0 8 # 9 # Unless required by applicable law or agreed to in writing, software 10 # distributed under the License is distributed on an "AS IS" BASIS, 11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 # See the License for the specific language governing permissions and 13 # limitations under the License. 14 # 15 # Requirement: Any integration or derivative work must explicitly attribute 16 # Tencent Zhuque Lab (https://github.com/Tencent/AI-Infra-Guard) in its 17 # documentation or user interface, as detailed in the NOTICE file. 18 19 import random 20 from deepteam.attacks import BaseAttack 21 from deepteam.attacks.single_turn.stratasword.template import ( 22 StrataSwordTemplate, 23 ) 24 25 from deepteam.utils import judge_language 26 27 class Opposing(BaseAttack): 28 29 def __init__(self, weight: int = 1): 30 self.weight = weight 31 32 def enhance(self, attack: str) -> str: 33 if judge_language(attack) == "chinese": 34 enhancement_methods = [ 35 StrataSwordTemplate.generate_opposing_1_zh, 36 StrataSwordTemplate.generate_opposing_2_zh, 37 StrataSwordTemplate.generate_opposing_3_zh 38 ] 39 else: 40 enhancement_methods = [ 41 StrataSwordTemplate.generate_opposing_1_en, 42 StrataSwordTemplate.generate_opposing_2_en, 43 StrataSwordTemplate.generate_opposing_3_en 44 ] 45 46 method = random.choice(enhancement_methods) 47 prompt = method(attack) 48 return prompt