Enyan Dai
2 papers · Latest:
Cryptography & Security
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
R$^2$A is a novel black-box attack that manipulates LLM routers to select expensive models, demonstrating a new security vulnerability.
2604.15022
Machine LearningCAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation
CAGenMol is a condition-aware discrete diffusion language model that uses RL for goal-directed molecular generation, handling complex constraints and non-differentiable objectives.
2604.11483
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.