19 citations · 25 across the 5 of their papers we have counts for
6 papers
A Utility-Preserving Obfuscation Approach for YouTube Recommendations
Jiang Zhang, Hadi Askari, Konstantinos Psounis +1
Online content platforms optimize engagement by providing personalized recommendations to their users. These recommendation systems track and profile users to predict relevant cont…
Nowhere to Hide: Detecting Obfuscated Fingerprinting Scripts
Ray Ngan, Surya Konkimalla, Zubair Shafiq
As the web moves away from stateful tracking, browser fingerprinting is becoming more prevalent. Unfortunately, existing approaches to detect browser fingerprinting do not take int…
YouTube, The Great Radicalizer? Auditing and Mitigating Ideological Biases in YouTube Recommendations
Muhammad Haroon, Anshuman Chhabra, Xin Liu +3
Recommendations algorithms of social media platforms are often criticized for placing users in "rabbit holes" of (increasingly) ideologically biased content. Despite these concerns…
HARPO: Learning to Subvert Online Behavioral Advertising
Jiang Zhang, Konstantinos Psounis, Muhammad Haroon +1
Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat. Unfortunately, existing privacy-enhancing tools are not always effective agai…
Fingerprinting Fine-tuned Language Models in the Wild
Nirav Diwan, Tanmoy Chakravorty, Zubair Shafiq
There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the re…
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective
Shahbaz Rezaei, Zubair Shafiq, Xin Liu
Deep ensemble learning has been shown to improve accuracy by training multiple neural networks and averaging their outputs. Ensemble learning has also been suggested to defend agai…