# anomaly-detection
標記為「anomaly-detection」的 19 篇文章
Inference Log Analysis
Analyzing inference logs for AI forensic investigation: detecting anomalous patterns, identifying jailbreak attempts through metadata, token-level analysis, and latency anomaly detection.
Monitoring & Detection Assessment
Test your understanding of AI security monitoring, anomaly detection, logging strategies, and incident detection for LLM-based applications with 9 intermediate-level questions.
LLM Monitoring and Anomaly Detection
Building monitoring systems that detect adversarial usage patterns in LLM applications.
AI Anomaly Detection
Detecting jailbreak attempts, unusual usage patterns, output drift, and embedding space anomalies in AI systems through statistical and ML-based methods.
Runtime Monitoring & Anomaly Detection
Monitoring LLM applications in production for token usage anomalies, output pattern detection, behavioral drift, and using tools like Langfuse, Helicone, and custom logging.
Token-Level Anomaly Detection
Building token-level anomaly detection systems that identify adversarial patterns in input sequences.
Continuous Monitoring of Fine-Tuned Models
Post-deployment monitoring strategies for fine-tuned models -- drift detection, behavior baselines, automated re-evaluation, and anomaly detection to catch safety issues that pre-deployment testing missed.
Training Data Integrity
Defense-focused guide to ensuring training data has not been poisoned, covering label flipping, backdoor insertion, clean-label attacks, data validation pipelines, provenance tracking, and anomaly detection.
AI Monitoring Setup
Step-by-step walkthrough for implementing AI system monitoring: inference logging, behavioral anomaly detection, alert configuration, dashboard creation, and integration with existing SIEM platforms.
Anomaly Detection for LLM Traffic
Build anomaly detection for LLM API traffic to identify attack patterns, abuse, and prompt injection attempts.
推論記錄分析
為 AI 鑑識調查分析推論記錄：偵測異常模式、經 metadata 辨識越獄嘗試、token 層級分析與延遲異常偵測。
LLM Monitoring and Anomaly Detection
Building monitoring systems that detect adversarial usage patterns in LLM applications.
AI Anomaly Detection
Detecting jailbreak attempts, unusual usage patterns, output drift, and embedding space anomalies in AI systems through statistical and ML-based methods.
執行時監控與異常偵測
於生產中監控 LLM 應用之 token 使用異常、輸出模式偵測、行為漂移，並使用如 Langfuse、Helicone 與自訂記錄之工具。
Token-Level Anomaly Detection
Building token-level anomaly detection systems that identify adversarial patterns in input sequences.
Continuous Monitoring of Fine-Tuned 模型s
Post-deployment monitoring strategies for fine-tuned models -- drift detection, behavior baselines, automated re-evaluation, and anomaly detection to catch safety issues that pre-deployment testing missed.
訓練 Data Integrity
防禦-focused guide to ensuring training data has not been poisoned, covering label flipping, backdoor insertion, clean-label attacks, data validation pipelines, provenance tracking, and anomaly detection.
AI Monitoring Setup
Step-by-step walkthrough for implementing AI system monitoring: inference logging, behavioral anomaly detection, alert configuration, dashboard creation, and integration with existing SIEM platforms.
Anomaly Detection for LLM Traffic
Build anomaly detection for LLM API traffic to identify attack patterns, abuse, and prompt injection attempts.