1 code implementation • ACL 2022 • Wanyue Zhai, Jonathan Rusert, Zubair Shafiq, Padmini Srinivasan
Our results motivate the need to develop authorship obfuscation approaches that are resistant to deobfuscation.
no code implementations • 16 Aug 2023 • Brijesh Vora, Kartik Patwari, Syed Mahbub Hafiz, Zubair Shafiq, Chen-Nee Chuah
Our findings reveal that while the benefits of pruning enhanced generalizability, compression, and faster inference times are preserved, adversarial robustness remains comparable to the base model.
1 code implementation • 7 Aug 2023 • Shaoor Munir, Patrick Lee, Umar Iqbal, Zubair Shafiq, Sandra Siby
While privacy-focused browsers have taken steps to block third-party cookies and mitigate browser fingerprinting, novel tracking techniques that can bypass existing countermeasures continue to emerge.
1 code implementation • 22 Mar 2022 • Wanyue Zhai, Jonathan Rusert, Zubair Shafiq, Padmini Srinivasan
Specifically, they are not evaluated against adversarially trained authorship attributors that are aware of potential obfuscation.
1 code implementation • ACL 2022 • Jonathan Rusert, Zubair Shafiq, Padmini Srinivasan
Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale.
1 code implementation • 25 Feb 2022 • Hieu Le, Salma Elmalaki, Athina Markopoulou, Zubair Shafiq
AutoFR is effective: it generates filter rules that can block 86% of the ads, as compared to 87% by EasyList, while achieving comparable visual breakage.
no code implementations • 9 Nov 2021 • Jiang Zhang, Konstantinos Psounis, Muhammad Haroon, Zubair Shafiq
Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat.
no code implementations • 15 Sep 2021 • Muhammad Haroon, Fareed Zaffar, Padmini Srinivasan, Zubair Shafiq
Our experiments show that if an obfuscator can evade an ensemble attribution classifier, which is based on multiple base attribution classifiers, it is more likely to transfer to different attribution classifiers.
1 code implementation • Findings (ACL) 2021 • Nirav Diwan, Tanmoy Chakravorty, Zubair Shafiq
Prior work on fingerprinting LMs is limited to attributing synthetic text generated by a handful (usually < 10) of pre-trained LMs.
1 code implementation • 12 May 2021 • Shahbaz Rezaei, Zubair Shafiq, Xin Liu
We analyze the impact of various factors in deep ensembles and demonstrate the root cause of the trade-off.
no code implementations • EACL 2021 • Shaoor Munir, Brishna Batool, Zubair Shafiq, Padmini Srinivasan, Fareed Zaffar
Given the potential misuse of recent advances in synthetic text generation by language models (LMs), it is important to have the capacity to attribute authorship of synthetic text.
1 code implementation • ACL 2020 • Asad Mahmood, Zubair Shafiq, Padmini Srinivasan
Authorship attribution aims to identify the author of a text based on the stylometric analysis.
no code implementations • 29 Jan 2020 • Shitong Zhu, Zhongjie Wang, Xun Chen, Shasha Li, Umar Iqbal, Zhiyun Qian, Kevin S. Chan, Srikanth V. Krishnamurthy, Zubair Shafiq
Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful.
1 code implementation • 22 May 2018 • Umar Iqbal, Peter Snyder, Shitong Zhu, Benjamin Livshits, Zhiyun Qian, Zubair Shafiq
AdGraph differs from existing approaches by building a graph representation of the HTML structure, network requests, and JavaScript behavior of a webpage, and using this unique representation to train a classifier for identifying advertising and tracking resources.