most citedPart-Based Models Improve Adversarial Robustness

2 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CR2025

Defending Against Prompt Injection With a Few DefensiveTokens

Sizhe Chen, Yizhu Wang, Nicholas Carlini +2

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting inst…

cs.CV2022★ 2 cited

Part-Based Models Improve Adversarial Robustness

Chawin Sitawarin, Kornrapat Pongmala, Yizheng Chen +2

We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks by introducing a part-based model for object classification…