├── api └── OAI_CONFIG_LIST ├── assets ├── logo.png └── pipeline.jpg ├── configs ├── hi_traits.yaml ├── hi_traits_clean.yaml └── hi_traits_debate.yaml ├── data ├── data_base.csv └── data_tiny.xlsx ├── groupchat.py ├── prompts ├── agentsafety │ ├── base │ │ ├── ai_assistant.txt │ │ ├── ai_user.txt │ │ ├── ai_user_ori.txt │ │ ├── critic.txt │ │ └── debate.txt │ ├── camel │ │ ├── ai_assistant.txt │ │ └── ai_user.txt │ ├── human_injection.yaml │ └── task_specifier.txt ├── current_attack_method │ └── jailbreakchat.txt ├── eval_gpt │ └── eval_gpt_dangerous.txt ├── moral_rules │ └── moral.yaml └── psy_test │ └── DTDD_new.txt ├── readme.md ├── result_extract.py ├── round_extract.py ├── start.py ├── universal_agent.py └── utils.py /api/OAI_CONFIG_LIST: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/api/OAI_CONFIG_LIST -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/assets/logo.png -------------------------------------------------------------------------------- /assets/pipeline.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/assets/pipeline.jpg -------------------------------------------------------------------------------- /configs/hi_traits.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/configs/hi_traits.yaml -------------------------------------------------------------------------------- /configs/hi_traits_clean.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/configs/hi_traits_clean.yaml -------------------------------------------------------------------------------- /configs/hi_traits_debate.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/configs/hi_traits_debate.yaml -------------------------------------------------------------------------------- /data/data_base.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/data/data_base.csv -------------------------------------------------------------------------------- /data/data_tiny.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/data/data_tiny.xlsx -------------------------------------------------------------------------------- /groupchat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/groupchat.py -------------------------------------------------------------------------------- /prompts/agentsafety/base/ai_assistant.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/base/ai_assistant.txt -------------------------------------------------------------------------------- /prompts/agentsafety/base/ai_user.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/base/ai_user.txt -------------------------------------------------------------------------------- /prompts/agentsafety/base/ai_user_ori.txt: -------------------------------------------------------------------------------- 1 | Creative in software product ideas. -------------------------------------------------------------------------------- /prompts/agentsafety/base/critic.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/base/critic.txt -------------------------------------------------------------------------------- /prompts/agentsafety/base/debate.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/base/debate.txt -------------------------------------------------------------------------------- /prompts/agentsafety/camel/ai_assistant.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/camel/ai_assistant.txt -------------------------------------------------------------------------------- /prompts/agentsafety/camel/ai_user.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/camel/ai_user.txt -------------------------------------------------------------------------------- /prompts/agentsafety/human_injection.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/human_injection.yaml -------------------------------------------------------------------------------- /prompts/agentsafety/task_specifier.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/agentsafety/task_specifier.txt -------------------------------------------------------------------------------- /prompts/current_attack_method/jailbreakchat.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/current_attack_method/jailbreakchat.txt -------------------------------------------------------------------------------- /prompts/eval_gpt/eval_gpt_dangerous.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/eval_gpt/eval_gpt_dangerous.txt -------------------------------------------------------------------------------- /prompts/moral_rules/moral.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/moral_rules/moral.yaml -------------------------------------------------------------------------------- /prompts/psy_test/DTDD_new.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/prompts/psy_test/DTDD_new.txt -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/readme.md -------------------------------------------------------------------------------- /result_extract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/result_extract.py -------------------------------------------------------------------------------- /round_extract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/round_extract.py -------------------------------------------------------------------------------- /start.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/start.py -------------------------------------------------------------------------------- /universal_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/universal_agent.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AI4Good24/PsySafe/HEAD/utils.py --------------------------------------------------------------------------------