Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Veldanda, Akshaj Kumar"'
Autor:
Veldanda, Akshaj Kumar, Zhang, Shi-Xiong, Das, Anirban, Chakraborty, Supriyo, Rawls, Stephen, Sahu, Sambit, Naphade, Milind
Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying LLMs to un
Externí odkaz:
http://arxiv.org/abs/2409.13054
Autor:
Veldanda, Akshaj Kumar, Grob, Fabian, Thakur, Shailja, Pearce, Hammond, Tan, Benjamin, Karri, Ramesh, Garg, Siddharth
Large Language Models (LLMs) such as GPT-3.5, Bard, and Claude exhibit applicability across numerous tasks. One domain of interest is their use in algorithmic hiring, specifically in matching resumes with job categories. Yet, this introduces issues o
Externí odkaz:
http://arxiv.org/abs/2310.05135
Spam filters are a crucial component of modern email systems, as they help to protect users from unwanted and potentially harmful emails. However, the effectiveness of these filters is dependent on the quality of the machine learning models that powe
Externí odkaz:
http://arxiv.org/abs/2307.09649
Autor:
Pfeiffer, Kai, Jia, Yuze, Yin, Mingsheng, Veldanda, Akshaj Kumar, Hu, Yaqi, Trivedi, Amee, Zhang, Jeff, Garg, Siddharth, Erkip, Elza, Rangan, Sundeep, Righetti, Ludovic
In this paper, we study a navigation problem where a mobile robot needs to locate a mmWave wireless signal. Using the directionality properties of the signal, we propose an estimation and path planning algorithm that can efficiently navigate in clutt
Externí odkaz:
http://arxiv.org/abs/2303.03739
Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although sensitive attributes are typically assumed to be known during training, th
Externí odkaz:
http://arxiv.org/abs/2302.01385
Autor:
Veldanda, Akshaj Kumar, Brugere, Ivan, Chen, Jiahao, Dutta, Sanghamitra, Mishler, Alan, Garg, Siddharth
The success of DNNs is driven by the counter-intuitive ability of over-parameterized networks to generalize, even when they perfectly fit the training data. In practice, test error often continues to decrease with increasing over-parameterization, re
Externí odkaz:
http://arxiv.org/abs/2206.14853
Autor:
Fu, Hao, Veldanda, Akshaj Kumar, Krishnamurthy, Prashanth, Garg, Siddharth, Khorrami, Farshad
Publikováno v:
IEEE Access 10 (2022): 5545-5558
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of a backdoo
Externí odkaz:
http://arxiv.org/abs/2011.02526
Autor:
Veldanda, Akshaj Kumar, Liu, Kang, Tan, Benjamin, Krishnamurthy, Prashanth, Khorrami, Farshad, Karri, Ramesh, Dolan-Gavitt, Brendan, Garg, Siddharth
This paper proposes a novel two-stage defense (NNoculation) against backdoored neural networks (BadNets) that, repairs a BadNet both pre-deployment and online in response to backdoored test inputs encountered in the field. In the pre-deployment stage
Externí odkaz:
http://arxiv.org/abs/2002.08313
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Khan, Vishwas Chandra1 vk13@iitbbs.ac.in, Veldanda, Akshaj Kumar1 akv12@iitbbs.ac.in, Balaganesan, G.2 gbganesh@iitm.ac.in, Sivakumar, M. S.2 mssiva@iitm.ac.in
Publikováno v:
Latin American Journal of Solids & Structures. 2018, Vol. 15 Issue 4, p1-18. 18p.