# adapter
8 artikelengetagd met “adapter”
Beveiligingsanalyse van adapterlagen
Security analysis of adapter-based fine-tuning including LoRA, prefix tuning, and prompt tuning.
Aanvalsvectoren op adapterlagen
Comprehensive analysis of attack vectors targeting parameter-efficient adapter layers including LoRA, QLoRA, and prefix tuning modules.
Adapter poisoning-aanvallen
Poisoning publicly shared adapters and LoRA weights to compromise downstream users.
Injection van kwaadaardige adapters
How attackers craft LoRA adapters containing backdoors, distribute poisoned adapters through model hubs, and exploit adapter stacking to compromise model safety -- techniques, detection challenges, and real-world supply chain risks.
Aanvalsoppervlak van LoRA en adapters
Overview of security vulnerabilities in parameter-efficient fine-tuning methods including LoRA, QLoRA, and adapter-based approaches -- how the efficiency and shareability of adapters create novel attack vectors.
Directe manipulatie van gewichten
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.
Beveiligingsrisico's van gedeelde adapters
Security risks of using publicly shared adapters from model hubs and community repositories.
LoRA- & adapterlaag-aanvallen
Beveiligingsimplicaties van LoRA en op adapters gebaseerde fine-tuning, waaronder het verwijderen van safety-alignment, adaptervergiftiging, rangmanipulatie-aanvallen en het misbruik van multi-adapter-conflicten.