124 citations · 158 across the 5 of their papers we have counts for
5 papers
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Yangsibo Huang, Samyak Gupta, Mengzhou Xia +2
The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behav…
Privacy Implications of Retrieval-Based Language Models
Yangsibo Huang, Samyak Gupta, Zexuan Zhong +2
Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieve…
Recovering Private Text in Federated Learning of Language Models
Samyak Gupta, Yangsibo Huang, Zexuan Zhong +3
Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eaves…
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
Yangsibo Huang, Samyak Gupta, Zhao Song +2
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or…
Distill: Domain-Specific Compilation for Cognitive Models
Jan Vesely, Raghavendra Pradyumna Pothukuchi, Ketaki Joshi +3
This paper discusses our proposal and implementation of Distill, a domain-specific compilation tool based on LLVM to accelerate cognitive models. Cognitive models explain the proce…