| { | |
| "base_model": "all-mpnet-base-v2", | |
| "embedding_dim": 768, | |
| "max_seq_length": 512, | |
| "multiclass": true, | |
| "num_classes": 26, | |
| "label_mapping": { | |
| "0": "Benign", | |
| "1": "Social Engineering & Manipulation", | |
| "2": "Adversarial Reasoning", | |
| "3": "Output Integrity & Reliability", | |
| "4": "Context and Memory Exploitation", | |
| "5": "Reasoning and Logic Subversion", | |
| "6": "Role-Playing and Identity Confusion", | |
| "7": "Technical and Encoding Attacks", | |
| "8": "Ethical Boundary Testing", | |
| "9": "Temporal and Sequential Manipulation", | |
| "10": "Output Format and Structure Exploitation", | |
| "11": "Domain-Specific Safety Bypasses", | |
| "12": "Psychological and Cognitive Exploitation", | |
| "13": "Multi-Modal and Cross-Domain Attacks", | |
| "14": "Resource and Performance Exploitation", | |
| "15": "Social and Cultural Manipulation", | |
| "16": "Adversarial Collaboration", | |
| "17": "Feedback and Learning Exploitation", | |
| "18": "Adversarial Robustness Testing", | |
| "19": "Emergent Behavior and Capability Exploitation", | |
| "20": "Uncertainty and Confidence Manipulation", | |
| "21": "Knowledge Base and Training Data Exploitation", | |
| "22": "Behavioral Conditioning and Adaptation", | |
| "23": "System Integration and API Exploitation", | |
| "24": "Privacy & Data Security", | |
| "25": "Prompt Manipulation & Instruction Adherence" | |
| } | |
| } |