Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Vinu Sankar"'
Autor:
Sounetra Choudhury, Sandip Ghosh, Prosenjeet Chakraborty, Sayari Pal, Koustuv Ghosh, Subhankar Saha, Jitesh Midha, Vinu Sankar, Abhisek Mohata, Bitan Kumar Chattopadhyay, Shibajyoti Ghosh, Soumen Das, Biswarup Basu, Nilabja Sikdar
Publikováno v:
BMC Gastroenterology, Vol 24, Iss 1, Pp 1-21 (2024)
Abstract Background and introduction Two and half percent of the Indian population suffer from gallbladder cancer (GBC). The primary factors that lead GBC are associated with mutation of several protooncogenes such as EGFR, ERBB2, Myc, and CCND1 alon
Externí odkaz:
https://doaj.org/article/2851fcba53e8421e8e44c2d035b5daa0
Identifying the origin of data is crucial for data provenance, with applications including data ownership protection, media forensics, and detecting AI-generated content. A standard approach involves embedding-based retrieval techniques that match qu
Externí odkaz:
http://arxiv.org/abs/2406.02836
Autor:
Sadasivan, Vinu Sankar, Saha, Shoumik, Sriramanan, Gaurang, Kattakinda, Priyatham, Chegini, Atoosa, Feizi, Soheil
In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability o
Externí odkaz:
http://arxiv.org/abs/2402.15570
Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations, known as adversarial attacks. On the other hand, prior works have also
Externí odkaz:
http://arxiv.org/abs/2310.19889
Autor:
Saberi, Mehrdad, Sadasivan, Vinu Sankar, Rezaei, Keivan, Kumar, Aounon, Chegini, Atoosa, Wang, Wenxiao, Feizi, Soheil
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have been intr
Externí odkaz:
http://arxiv.org/abs/2310.00076
The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an expectation over
Externí odkaz:
http://arxiv.org/abs/2303.16308
The unregulated use of LLMs can potentially lead to malicious consequences such as plagiarism, generating fake news, spamming, etc. Therefore, reliable detection of AI-generated text can be critical to ensure the responsible use of LLMs. Recent works
Externí odkaz:
http://arxiv.org/abs/2303.11156
Large-scale training of modern deep learning models heavily relies on publicly available data on the web. This potentially unauthorized usage of online data leads to concerns regarding data privacy. Recent works aim to make unlearnable data for deep
Externí odkaz:
http://arxiv.org/abs/2303.04278
Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum ordering,
Externí odkaz:
http://arxiv.org/abs/2103.00147
Publikováno v:
Materials Today: Proceedings. 80:2207-2217
The depleting fuel resources and elevated air pollution are raising serious concerns among the global population. The fuel prices are also increasing day by day. Hence the world is more focused on maximizing conventional energy resources like solar,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c622032fc4adefdd61afecefeb946d5
https://doi.org/10.1016/j.matpr.2021.06.180
https://doi.org/10.1016/j.matpr.2021.06.180