Search Results for author:
Found 14 papers, 9 papers with code
Adversarial Authorship Attribution for Deobfuscation
Our results motivate the need to develop authorship obfuscation approaches that are resistant to deobfuscation.
Benchmarking Adversarial Robustness of Compressed Deep Learning Models
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.
PURL: Safe and Effective Sanitization of Link Decoration
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.
A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscation
Specifically, they are not evaluated against adversarially trained authorship attributors that are aware of potential obfuscation.
On The Robustness of Offensive Language Classifiers
Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale.
AutoFR: Automated Filter Rule Generation for Adblocking
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.
HARPO: Learning to Subvert Online Behavioral Advertising
Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat.
Avengers Ensemble! Improving Transferability of Authorship Obfuscation
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.
Fingerprinting Fine-tuned Language Models in the Wild
Prior work on fingerprinting LMs is limited to attributing synthetic text generated by a handful (usually < 10) of pre-trained LMs.
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective
We analyze the impact of various factors in deep ensembles and demonstrate the root cause of the trade-off.
Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models
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.
A Girl Has A Name: Detecting Authorship Obfuscation
Authorship attribution aims to identify the author of a text based on the stylometric analysis.
A4 : Evading Learning-based Adblockers
Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful.
AdGraph: A Graph-Based Approach to Ad and Tracker Blocking
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.
