# ai-forensics-ir
23 articlestagged with “ai-forensics-ir”
Adversarial Input Forensics
Forensic techniques for identifying, reconstructing, and analyzing adversarial inputs used to manipulate AI system behavior.
AI Honeypot Forensics
Designing and operating AI honeypots for threat intelligence collection, and forensic analysis of captured adversarial interactions.
AI Incident Legal Considerations
Legal frameworks, obligations, and considerations for organizations responding to AI security incidents, including evidence handling, regulatory reporting, and liability.
AI Incident Severity Scoring
Frameworks and methodologies for scoring the severity of AI security incidents, integrating NIST AI RMF, MITRE ATLAS, and traditional CVSS approaches.
AI Red Team Evidence Collection
Systematic evidence collection methodologies for AI red team engagements, including artifact preservation, finding documentation, and chain of custody procedures.
AI Supply Chain Incident Response
Incident response procedures for compromises in the AI supply chain, including model repositories, training pipelines, and dependency chains.
AI System Audit Trail Design
Designing comprehensive audit trails for AI systems that support forensic investigation, regulatory compliance, and incident response.
AI System Memory Forensics
Memory forensics techniques for investigating compromised AI systems, including GPU memory analysis, model weight extraction, and runtime state recovery.
API Key Compromise Investigation
Investigating AI API key compromise incidents including detection, scope assessment, usage forensics, and remediation procedures.
Automated AI Incident Triage
Building automated triage systems for AI security incidents using rule-based engines, anomaly detection, and LLM-assisted classification.
Cloud AI Forensics: AWS
Forensic investigation techniques for AWS AI services including SageMaker, Bedrock, and associated infrastructure logging and evidence collection.
Cloud AI Forensics: Azure
Forensic investigation techniques for Azure AI services including Azure OpenAI, Azure ML, and Cognitive Services with diagnostic logging and evidence collection.
Deepfake Forensic Analysis
Forensic techniques for detecting, analyzing, and attributing AI-generated deepfake images, video, and audio content.
Fine-Tuning Attack Forensics
Forensic techniques for detecting unauthorized fine-tuning modifications to language models, including safety alignment degradation and capability injection.
LLM Conversation Forensics
Forensic analysis techniques for investigating LLM conversation logs, detecting manipulation patterns, and reconstructing attack timelines from chat histories.
LLM Output Watermark Detection
Techniques for detecting, extracting, and analyzing watermarks embedded in LLM-generated text for provenance tracking and forensic attribution.
Model Backdoor Detection Forensics
Forensic techniques for detecting, analyzing, and attributing backdoors implanted in machine learning models through training-time or post-training attacks.
Model Drift Forensics
Forensic techniques for distinguishing natural model drift from deliberate tampering, including statistical detection methods and evidence collection.
Multi-Model Attack Correlation
Techniques for correlating and analyzing coordinated attacks that target multiple AI models or systems within an organization.
Prompt Injection Chain Analysis
Analyzing chains of prompt injection attacks across multi-step AI systems, including indirect injection propagation, agentic exploitation, and cross-system attack correlation.
RAG Poisoning Forensics
Forensic investigation techniques for detecting and analyzing poisoning attacks against Retrieval-Augmented Generation systems.
Training Data Provenance Forensics
Forensic techniques for tracing the origins, lineage, and integrity of training data used in machine learning models.
Vector Database Forensics
Forensic analysis techniques for detecting and investigating vector database poisoning, unauthorized modifications, and data integrity violations.