4 papers
Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
Onur Alp Kirci, M. Emre Gursoy
Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high a…
LDP: An Extensible and Multi-Threaded Toolkit for Local Differential Privacy Protocols and Post-Processing Methods
Berkay Kemal Balioglu, Alireza Khodaie, Mehmet Emre Gursoy
Local differential privacy (LDP) has become a prominent notion for privacy-preserving data collection. While numerous LDP protocols and post-processing (PP) methods have been devel…
Don't Hash Me Like That: Exposing and Mitigating Hash-Induced Unfairness in Local Differential Privacy
Berkay Kemal Balioglu, Alireza Khodaie, Mehmet Emre Gursoy
Local differential privacy (LDP) has become a widely accepted framework for privacy-preserving data collection. In LDP, many protocols rely on hash functions to implement user-side…
Injecting Bias into Text Classification Models using Backdoor Attacks
A. Dilara Yavuz, M. Emre Gursoy
The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classificati…