11 papers
Bowling with ChatGPT: On the Evolving User Interactions with Conversational AI Systems
Sai Keerthana Karnam, Abhisek Dash, Krishna P. Gummadi +3
Recent studies have discussed how users are increasingly using conversational AI systems, powered by LLMs, for information seeking, decision support, and even emotional support. Ho…
Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail Prediction
Sagnik Basu, Shubham Prakash, Ashish Maruti Barge +4
Large language models (LLMs) have been extensively used for legal judgment prediction tasks based on case reports and crime history. However, with a surge in the availability of la…
ASR-FAIRBENCH: Measuring and Benchmarking Equity Across Speech Recognition Systems
Anand Rai, Satyam Rahangdale, Utkarsh Anand +1
Automatic Speech Recognition (ASR) systems have become ubiquitous in everyday applications, yet significant disparities in performance across diverse demographic groups persist. In…
Exploring Disparity-Accuracy Trade-offs in Face Recognition Systems: The Role of Datasets, Architectures, and Loss Functions
Siddharth D Jaiswal, Sagnik Basu, Sandipan Sikdar +1
Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of…
Setting the Course, but Forgetting to Steer: Analyzing Compliance with GDPR's Right of Access to Data by Instagram, TikTok, and YouTube
Sai Keerthana Karnam, Abhisek Dash, Antariksh Das +6
The GDPR's Right of Access aims to empower users with control over their personal data via Data Download Packages (DDPs). However, their effectiveness is often compromised by incon…
DENOASR: Debiasing ASRs through Selective Denoising
Anand Kumar Rai, Siddharth D Jaiswal, Shubham Prakash +2
Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits,…
Sponsored is the New Organic: Implications of Sponsored Results on Quality of Search Results in the Amazon Marketplace
Abhisek Dash, Saptarshi Ghosh, Animesh Mukherjee +2
Interleaving sponsored results (advertisements) amongst organic results on search engine result pages (SERP) has become a common practice across multiple digital platforms. Adverti…
Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems
Siddharth D Jaiswal, Animesh Ganai, Abhisek Dash +2
Facial Recognition Systems (FRSs) are being developed and deployed globally at unprecedented rates. Most platforms are designed in a limited set of countries but deployed in worldw…
Auditing the Grid-Based Placement of Private Label Products on E-commerce Search Result Pages
Siddharth D Jaiswal, Abhisek Dash, Nitika Shroff +3
E-commerce platforms support the needs and livelihoods of their two most important stakeholders -- customers and producers/sellers. Multiple algorithmic systems, like ``search'' sy…
Mask-up: Investigating Biases in Face Re-identification for Masked Faces
Siddharth D Jaiswal, Ankit Kr. Verma, Animesh Mukherjee
AI based Face Recognition Systems (FRSs) are now widely distributed and deployed as MLaaS solutions all over the world, moreso since the COVID-19 pandemic for tasks ranging from va…
Auditing Gender Analyzers on Text Data
Siddharth D Jaiswal, Ankit Kumar Verma, Animesh Mukherjee
AI models have become extremely popular and accessible to the general public. However, they are continuously under the scanner due to their demonstrable biases toward various secti…