vix.ing · top · new · best · stats · spec

Vega, Jason

  1. Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
    2023/12/19 by Jason Vega, Isha Chaudhary, Vega, Jason +5 · 7 citations
    Computer Science · #Advanced Malware Detection Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Web Application Security Vulnerabilities
  2. Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
    2024/11/05 by Jason Vega, Junsheng Huang, Vega, Jason +6 · 1 citation
    Mathematics · Decision Sciences · Computer Science · #Statistical Methods in Clinical Trials #Simulation Techniques and Applications #Machine Learning and Algorithms