290 citations · 1.1k across the 23 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2023★ 14 cited
On the Exploitability of Instruction Tuning
Manli Shu, Jiongxiao Wang, Chen Zhu +3
Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning…
cs.CR2020★ 78 cited
Certified Defenses for Adversarial Patches
Ping-Yeh Chiang, Renkun Ni, Ahmed Abdelkader +3
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against…