papers

Publications (8)

cs.CR2022

Deepfake Text Detection: Limitations and Opportunities

Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah +5

Recent advances in generative models for language have enabled the creation of convincing synthetic text or deepfake text. Prior work has demonstrated the potential for misuse of d…

cs.CR2021

T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification

Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed +5

Deep Neural Network (DNN) classifiers are known to be vulnerable to Trojan or backdoor attacks, where the classifier is manipulated such that it misclassifies any input containing…

cs.CR2021

Deepfake Videos in the Wild: Analysis and Detection

Jiameng Pu, Neal Mangaokar, Lauren Kelly +5

AI-manipulated videos, commonly known as deepfakes, are an emerging problem. Recently, researchers in academia and industry have contributed several (self-created) benchmark deepfa…

cs.NI2018

Exploring Server-side Blocking of Regions

Sadia Afroz, Michael Carl Tschantz, Shaarif Sajid +3

One of the Internet's greatest strengths is the degree to which it facilitates access to any of its resources from users anywhere in the world. However, users in the developing wor…

cs.CR2016

Ad-Blocking and Counter Blocking: A Slice of the Arms Race

Rishab Nithyanand, Sheharbano Khattak, Mobin Javed +6

Adblocking tools like Adblock Plus continue to rise in popularity, potentially threatening the dynamics of advertising revenue streams. In response, a number of publishers have ram…

cs.NI2018

A Bestiary of Blocking: The Motivations and Modes behind Website Unavailability

Sadia Afroz, Mobin Javed, Vern Paxson +3

This paper examines different reasons the websites may vary in their availability by location. Prior works on availability mostly focus on censorship by nation states. We look at t…

cs.CR2026

Can You Tell It's AI? Human Perception of Synthetic Voices in Vishing Scenarios

Zoha Hayat Bhatti, Bakhtawar Ahtisham, Seemal Tausif +3

Large Language Models and commercial speech synthesis systems now enable highly realistic AI-generated voice scams (vishing), raising urgent concerns about deception at scale. Yet…

stat.AP2017

Applying Machine Learning Methods to Enhance the Distribution of Social Services in Mexico

Kris Sankaran, Diego Garcia-Olano, Mobin Javed +7

The Government of Mexico's social development agency, SEDESOL, is responsible for the administration of social services and has the mission of lifting Mexican families out of pover…