Abstract

We introduce a family of information leakage measures called maximal (α,β) -leakage ( Mα beL), parameterized by real numbers α and β greater than or equal to 1. The measure is formalized via an operational definition involving an adversary guessing an unknown (randomized) function of the data given the released data. We obtain a simplified computable expression for the measure and show that it satisfies several basic properties such as monotonicity in β for a fixed α , non-negativity, data processing inequalities, and additivity over independent releases. We highlight the relevance of this family by showing that it bridges several known leakage measures, including maximal α -leakage (β=1) , maximal leakage (α=∞,β=1) , local differential privacy (LDP) (α=∞,β=∞) , and local Rényi differential privacy (LRDP) (α=β) , thereby giving an operational interpretation to local Rényi differential privacy. We also study a conditional version of Mα beL on leveraging which we recover differential privacy and Rényi differential privacy. A new variant of LRDP, which we call maximal Rényi leakage, appears as a special case of Mα beL for α=∞ that smoothly tunes between maximal leakage ( β=1 ) and LDP ( β=∞ ). Finally, we show that a vector form of the maximal Rényi leakage relaxes differential privacy under Gaussian and Laplacian mechanisms.

Abstract

Generative adversarial networks (GANs), modeled as a zero-sum game between a generator (G) and a discriminator (D), allow generating synthetic data with formal guarantees. Noting that D is a classifier, we begin by reformulating the GAN value function using class probability estimation (CPE) losses. We prove a two-way correspondence between CPE loss GANs and f-GANs which minimize f-divergences. We also show that all symmetric f-divergences are equivalent in convergence. In the finite sample and model capacity setting, we define and obtain bounds on estimation and generalization errors. We specialize these results to α -GANs, defined using α -loss, a tunable CPE loss family parametrized by α∈(0,∞ ]. We next introduce a class of dual-objective GANs to address training instabilities of GANs by modeling each player’s objective using α -loss to obtain (αD,αG) -GANs. We show that the resulting non-zero sum game simplifies to minimizing an f-divergence under appropriate conditions on (αD,αG) . Generalizing this dual-objective formulation using CPE losses, we define and obtain upper bounds on an appropriately defined estimation error. Finally, we highlight the value of tuning (αD,αG) in alleviating training instabilities for the synthetic 2D Gaussian mixture ring as well as the large publicly available Celeb-A and LSUN Classroom image datasets.

Abstract

Distracted driving is a leading cause of road accidents globally. Identifying distracted driving involves reliably detecting and classifying various forms of driver distraction (e.g., texting, eating, or using in-car devices) from in-vehicle camera feeds to enhance road safety. This task is challenging due to the need for robust models that can generalize to a diverse set of driver behaviors without requiring extensive annotated datasets. In this paper, we propose KiD3, a novel method for distracted driver detection (DDD) that infuses auxiliary knowledge about semantic relations between entities in a scene and the structural configuration of the driver’s pose. Specifically, we construct a unified framework that integrates scene graphs and driver pose information with visual cues from video frames to create a holistic representation of the driver’s actions. Our results indicate that KiD3 achieves a 13.64% accuracy improvement over the vision-only baseline by incorporating auxiliary knowledge with visual information.

Abstract

Large Language Models (LLMs) have emerged as powerful tools to per- form various tasks in the legal domain, ranging from generating summaries to pre- dicting judgments. Despite their immense potential, these models have been proven to learn and exhibit societal biases and make unfair predictions. Hence, it is es- sential to evaluate these models prior to deployment. In this study, we explore the ability of LLMs to perform Binary Statutory Reasoning in the Indian legal land- scape across various societal disparities. We present a novel metric, β -weighted Le- gal Safety Score (LSSβ ), to evaluate the legal usability of the LLMs. Additionally, we propose a finetuning pipeline, utilising specialised legal datasets, as a potential method to reduce bias. Our proposed pipeline effectively reduces bias in the model, as indicated by improved LSSβ . This highlights the potential of our approach to enhance fairness in LLMs, making them more reliable for legal tasks in socially diverse contexts.

Abstract

This paper considers the problem of fair probabilistic binary classification with binary protected groups. The classifier assigns scores, and a practitioner predicts labels using a certain cut-off threshold based on the desired trade-off between false positives vs. false negatives. It derives these thresholds from the ROC of the classifier. The resultant classifier may be unfair to one of the two protected groups in the dataset. It is desirable that no matter what threshold the practitioner uses, the classifier should be fair to both the protected groups; that is, the L p norm between FPRs and TPRs of both the protected groups should be at most ε . We call such fairness on ROCs of both the protected attributes ε p -Equalized ROC. Given a classifier not satisfying ε 1 -Equalized ROC, we aim to design a post-processing method to transform the given (potentially unfair) classifier's output (score) to a suitable randomized yet fair classifier. That is, the resultant classifier must satisfy ε 1 -Equalized ROC. First, we introduce a threshold query model on the ROC curves for each protected group. The resulting classifier is bound to face a reduction in AUC. With the proposed query model, we provide a rigorous theoretical analysis of the minimal AUC loss to achieve ε 1 -Equalized ROC. To achieve this, we design a linear time algorithm, namely \texttt{FROC}, to transform a given classifier's output to a probabilistic classifier that satisfies ε 1 -Equalized ROC. We prove that under certain theoretical conditions, \texttt{FROC}\ achieves the theoretical optimal guarantees. We also study the performance of our \texttt{FROC}\ on multiple real-world datasets with many trained classifiers.

Abstract

This paper uses 3D stochastic geometry to analyse the coverage and meta-distribution (MD) performance of a low Earth orbit (LEO) satellite-based Internet-of-Things (IoT) network. The satellites are considered to be distributed at a fixed altitude around Earth following a Binomial point process. An IoT device broadcasts its sensed information to all the satellites with a line-of-sight within the visibility region and they act as selective decode-and-forward gateways. The ground server coherently combines the information received from multiple satellites. The analytically derived performance measures are verified through Monte Carlo simulations. The results demonstrate the impact of mega-LEO constellations on coverage and reliability, guiding 6G architecture design to improve connectivity and data offloading in smart cities and dense urban environments.

Abstract

A visual question answering (VQA) system for electrical circuit images could be useful as a quiz generator, design and verification assistant or an electrical diagnosis tool. Although there exists a vast literature on VQA, to the best of our knowledge, there is no existing work on VQA for electrical circuit images. To this end, we curate a new dataset, CircuitVQA, of 115K+ questions on 5725 electrical images with 70 circuit symbols. The dataset contains schematic as well as hand-drawn images. The questions span various categories like counting, value, junction and position based questions. To be effective, models must demonstrate skills like object detection, text recognition, spatial understanding, question intent understanding and answer generation. We experiment with multiple foundational visio-linguistic models for this task and find that a finetuned BLIP model with component descriptions as additional input provides best results. We make the code and dataset publicly available

Abstract

A system and method for implementing an experiment remotely and determining an output using a computer-vision model is provided. The system includes an image capturing device, an experiment setup, a microcontroller, a user device, and a relay unit. The microcontroller (i) receives the input of the experiment from the image capturing device,(ii) extracts one or more frames from the input data,(iii) pre-process the one or more frames to obtain a binary image,(iv) obtain a closed curve around the binary image to locate the experiment,(v) determine the coordinates of the experiment to track the experiment in each frame,(vi) determine an output of the experiment from every two consecutive frames of the one or more frames, and (vii) optimize the determined output of the experiment using a linear regression model.

Abstract

When novice engineers (fresh or recent graduates with little industry experience) join a SaaS (Software-as-a-Service) product company, they are tasked with comprehending the product, especially its behavior and dynamics. We believe that they can comprehend more effectively if they know and understand the architecture patterns used in the product. Are the current architecture pattern descriptions of high quality? Do they fit the needs of novice engineers? We evaluated the pattern descriptions of Model-View-Controller (MVC) (a popular and important architecture pattern for cloud systems) from a quality and fitment perspective and found gaps. To address these gaps, we have built a System of Systems (SoS) model of MVC that uses a transition systems vocabulary and a set-theoretic notation. In the paper, we show that this SoS model provides a rich set of information about the behavior and dynamics of the MVC components and their interactions. The model bridges the gaps in the MVC pattern description. One of the contributions of the paper is to provide criteria to evaluate the pattern descriptions for quality and fitment for novice engineers. The paper proposes that we augment the benchmark pattern description of MVC with an SoS model. The paper also demonstrates a general approach to building SoS models for architecture patterns and recommends creating a catalog of SoS models for SaaS architecture patterns. We believe such a catalog will significantly help novice engineers in comprehension and other software engineering activities.

Abstract

In literature, various time-frequency representation methods were investigated for automatic detection of voice disorders. Stockwell-Transform (S-Transform) provides good time-frequency localization; hence, it may efficiently capture the voice disorder related information from speech signal. With this motivation, we investigated different variants of S-Transform for the classification of voice disorders. This study proposed the S-Transform based cepstral coefficients for voice disorder detection and assessment. The performance of the proposed feature was compared with baseline features on SVD and HUPA databases. Compared to baseline features, proposed features performed best in terms of classification accuracy of 80.2% and 79.8% on HUPA and SVD databases, respectively for voice disorder detection task. Also, the proposed features performed better in case of assessment task. Further, the experimental results reveal that combining cepstral coefficients derived from S-Transform with baseline features improved the performance of proposed systems by 8% and 4% for detection and assessment tasks, respectively which highlights complementary nature of the explored features. We also analysed the effectiveness of S-Transform based spectral representation in capturing the acoustic characteristics for various voice qualities like breathiness, harshness, creakiness, and falsetto phonations. This representation was also compared with other time-frequency based methods such as STFT, ZTW and SFF. It was observed that S-Transform effectively captures the acoustic variations associated with different voice qualities compared to other baseline methods, which may be due to better spectro-temporal resolution offered by the S-Transform.