3 papers
cs.CR2025
Matching Ranks Over Probability Yields Truly Deep Safety Alignment
Jason Vega, Gagandeep Singh
Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for…
cs.LG2024
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
Jason Vega, Junsheng Huang, Gaokai Zhang +3
Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety…
cs.CR2024
Bypassing the Safety Training of Open-Source LLMs with Priming Attacks
Jason Vega, Isha Chaudhary, Changming Xu +1
With the recent surge in popularity of LLMs has come an ever-increasing need for LLM safety training. In this paper, we investigate the fragility of SOTA open-source LLMs under sim…