# hidden-behavior
2 articlestagged with “hidden-behavior”
Direct Weight Manipulation
Techniques for directly modifying LoRA adapter weights to bypass safety training, inject targeted capabilities, and hide malicious behaviors -- going beyond dataset-driven fine-tuning to surgical weight-level attacks.
weight-manipulationloraadaptersafety-bypasscapability-injectionhidden-behaviormodel-editing
Direct Weight Manipulation
Techniques for directly modifying LoRA adapter weights to bypass safety training, inject targeted capabilities, and hide malicious behaviors -- going beyond dataset-driven fine-tuning to surgical weight-level attacks.
weight-manipulationloraadaptersafety-bypasscapability-injectionhidden-behaviormodel-editing