
alibi-detect
Algorithms for outlier, adversarial and drift detection
adversarial-attackai-securityanomaly-detection+1
2.5k10 months ago

Algorithms for outlier, adversarial and drift detection

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"