Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Koneripalli, Kaushik"'
Autor:
Brahmachary, Shuvayan, Joshi, Subodh M., Panda, Aniruddha, Koneripalli, Kaushik, Sagotra, Arun Kumar, Patel, Harshil, Sharma, Ankush, Jagtap, Ameya D., Kalyanaraman, Kaushic
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, prompting interest in their application as black-box optimizers. This paper asserts that LLMs possess the capability for zero-shot optimization across diverse scenarios, i
Externí odkaz:
http://arxiv.org/abs/2403.02054
Autor:
Sur, Indranil, Sikka, Karan, Walmer, Matthew, Koneripalli, Kaushik, Roy, Anirban, Lin, Xiao, Divakaran, Ajay, Jha, Susmit
We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization). Recent work arXiv:2112.07668 has demonstrated successful backdoor attacks on multimodal models for the Visual Question Answering task. Their dual-ke
Externí odkaz:
http://arxiv.org/abs/2308.03906
Autor:
Acharya, Manoj, Roy, Anirban, Koneripalli, Kaushik, Jha, Susmit, Kanan, Christopher, Divakaran, Ajay
Publikováno v:
IJCAI-ECAI 2022
This paper presents an approach to detect out-of-context (OOC) objects in an image. Given an image with a set of objects, our goal is to determine if an object is inconsistent with the scene context and detect the OOC object with a bounding box. In t
Externí odkaz:
http://arxiv.org/abs/2202.05930