Search for: All records

Face recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets. Recent work in facial analysis and recognition have thus started making use of synthetic datasets generated from GANs and diffusion based generative models. These models, however, lack fairness in terms of demographic representation and can introduce the same biases in the trained downstream tasks. This can have serious societal and security implications. To address this issue, we propose a methodology that generates unbiased data from a biased generative model using an evolutionary algorithm. We show results for StyleGAN2 model trained on the Flicker Faces High Quality dataset to generate data for singular and combinations of demographic attributes such as Black and Woman. We generate a large racially balanced dataset of 13.5 million images, and show that it boosts the performance of facial recognition and analysis systems whilst reducing their biases. We have made our code-base ( https://github.com/anubhav1997/youneednodataset ) public to allow researchers to reproduce our work. 

A dictionary attack in a biometric system entails the use of a small number of strategically generated images or tem- plates to successfully match with a large number of identi- ties, thereby compromising security. We focus on dictionary attacks at the template level, specifically the IrisCodes used in iris recognition systems. We present an hitherto unknown vulnerability wherein we mix IrisCodes using simple bit- wise operators to generate alpha-mixtures —alpha-wolves (combining a set of “wolf” samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches. We evaluate this vulnerabil- ity using the IITD, CASIA-IrisV4-Thousand and Synthetic datasets, and observe that an alpha-wolf (from two wolves) can match upto 71 identities @FMR=0.001%, while an alpha-mammal (from two identities) can match upto 133 other identities @FMR=0.01% on the IITD dataset. 

Analysis of imaging sensors is one of the most reliable photo forensic techniques, but it is increasingly chal- lenged by complex image processing in modern cameras. The underlying photo response non-uniformity (PRNU) is distilled into a static sensor fingerprint unique for each device. This makes it easy to estimate and spoof and limits its reliability in face of sophisticated attackers. We propose to exploit computa- tional capabilities of emerging intelligent vision sensors to design next-generation computational sensor fingerprints. Such sensors allow for running neural network inference directly on raw pixels, which enables end-to-end optimization of the entire photo acquisition and distribution pipeline. Control over fingerprint generation allows for adaptation to various requirements and threat models. In this study we provide a detailed assessment of security properties and evaluate two approaches to prevent spoofing: fingerprint generation based on local image content and adversarial training. We found that adversarial training is currently impractical, but content fingerprints deliver good per- formance in the considered cross-domain (RAW-RGB) setting and could provide robust best-effort protection against photo manip- ulation. Moreover, computational fingerprints can alleviate other limitations of PRNU, e.g., its limited reliability for dark/texture content and expensive fingerprint storage that hinders scalability. To enable this line of work, we developed a novel open-source and high-fidelity simulation environment for modeling photo acquisi- tion and distribution pipelines (https://github.com/pkorus/neural- imaging). 

This work expands on previous advancements in genetic fingerprint spoofing via the DeepMasterPrints and introduces Diversity and Novelty MasterPrints. This system uses quality diversity evolutionary algorithms to generate dictionaries of artificial prints with a focus on increasing coverage of users from the dataset. The Diversity MasterPrints focus on generating solution prints that match with users not covered by previously found prints, and the Novelty MasterPrints explicitly search for prints with more that are farther in user space than previous prints. Our multi-print search methodologies outperform the singular DeepMasterPrints in both coverage and generalization while maintaining quality of the fingerprint image output. 

Misinformation has developed into a critical societal threat that can lead to disastrous societal consequences. Although fact-checking plays a key role in combating misinformation, relatively little research has empirically investigated work practices of professional fact-checkers. To address this gap, we conducted semi-structured interviews with 21 fact-checkers from 19 countries. The participants reported being inundated with information that needs filtering and prioritizing prior to fact-checking. The interviews surfaced a pipeline of practices fragmented across disparate tools that lack integration. Importantly, fact-checkers lack effective mechanisms for disseminating the outcomes of their efforts which prevents their work from fully achieving its potential impact. We found that the largely manual and labor intensive nature of current fact-checking practices is a barrier to scale. We apply these findings to propose a number of suggestions that can improve the effectiveness, efficiency, scale, and reach of fact-checking work and its outcomes.