1 code implementation • 24 Apr 2024 • Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala, Bimal Viswanath
Second, the emergence of \textit{vision foundation models} -- machine learning models trained on broad data that can be easily adapted to several downstream tasks -- can be misused by attackers to craft adversarial deepfakes that can evade existing defenses.
1 code implementation • 17 Oct 2022 • Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, Bimal Viswanath
Several defenses have been proposed for deepfake text detection.
no code implementations • 5 Apr 2021 • Neal Mangaokar, Jiameng Pu, Parantapa Bhattacharya, Chandan K. Reddy, Bimal Viswanath
The potential for fraudulent claims based on such generated 'fake' medical images is significant, and we demonstrate successful attacks on both X-rays and retinal fundus image modalities.
no code implementations • 15 Mar 2021 • Ya Xiao, Salman Ahmed, Wenjia Song, Xinyang Ge, Bimal Viswanath, Danfeng Yao
Despite recent research efforts, the vision of automatic code generation through API recommendation has not been realized.
1 code implementation • 7 Mar 2021 • Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K. Reddy, Bimal Viswanath
T-Miner employs a sequence-to-sequence (seq-2-seq) generative model that probes the suspicious classifier and learns to produce text sequences that are likely to contain the Trojan trigger.
1 code implementation • 7 Mar 2021 • Jiameng Pu, Neal Mangaokar, Lauren Kelly, Parantapa Bhattacharya, Kavya Sundaram, Mobin Javed, Bolun Wang, Bimal Viswanath
AI-manipulated videos, commonly known as deepfakes, are an emerging problem.
no code implementations • 17 May 2020 • Steve T.K. Jan, Qingying Hao, Tianrui Hu, Jiameng Pu, Sonal Oswal, Gang Wang, Bimal Viswanath
We evaluate this idea and show our method can train a model that outperforms existing methods with only 1% of the labeled data.
no code implementations • 27 Aug 2017 • Yuanshun Yao, Bimal Viswanath, Jenna Cryan, Hai-Tao Zheng, Ben Y. Zhao
Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers.
Cryptography and Security Social and Information Networks