# direct-preference-optimization
2 articlestagged with “direct-preference-optimization”
DPO-Specific Attacks
Vulnerabilities unique to Direct Preference Optimization -- reference model manipulation, KL divergence exploitation, and how DPO's mathematical framework creates attack surfaces not present in standard RLHF.
dpodirect-preference-optimizationreference-modelkl-divergencealignment-attackfine-tuning-security
DPO & Direct Alignment Attacks
Direct Preference Optimization vulnerabilities, how DPO differs from RLHF in attack surface, preference pair poisoning, and ranking manipulation techniques.
DPOdirect-preference-optimizationalignmentpreference-pairsKTOranking