Lin, Leon

1. Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
   2024/07/03 by Brown, Hannah, Lin, Leon, Kawaguchi, Kenji +1 · 4 citations
   #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. Single Character Perturbations Break LLM Alignment
   2024/07/03 by Leon Lin, H. Alex Brown, Lin, Leon +5 · 3 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques