9 citations · 26 across the 18 of their papers we have counts for
20 papers
Reconstructing Test Labels from Noisy Loss Functions
Abhinav Aggarwal, Shiva Prasad Kasiviswanathan, Zekun Xu +2
Machine learning classifiers rely on loss functions for performance evaluation, often on a private (hidden) dataset. In a recent line of research, label inference was introduced as…
Label Inference Attacks from Log-loss Scores
Abhinav Aggarwal, Shiva Prasad Kasiviswanathan, Zekun Xu +2
Log-loss (also known as cross-entropy loss) metric is ubiquitously used across machine learning applications to assess the performance of classification algorithms. In this paper,…
On a Utilitarian Approach to Privacy Preserving Text Generation
Zekun Xu, Abhinav Aggarwal, Oluwaseyi Feyisetan +1
Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. W…
Research Challenges in Designing Differentially Private Text Generation Mechanisms
Oluwaseyi Feyisetan, Abhinav Aggarwal, Zekun Xu +1
Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust.…
A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric
Zekun Xu, Abhinav Aggarwal, Oluwaseyi Feyisetan +1
Balancing the privacy-utility tradeoff is a crucial requirement of many practical machine learning systems that deal with sensitive customer data. A popular approach for privacy-pr…
Differentially Private Adversarial Robustness Through Randomized Perturbations
Nan Xu, Oluwaseyi Feyisetan, Abhinav Aggarwal +2
Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictio…
On Primes, Log-Loss Scores and (No) Privacy
Abhinav Aggarwal, Zekun Xu, Oluwaseyi Feyisetan +1
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditin…
LoCUS: A multi-robot loss-tolerant algorithm for surveying volcanic plumes
John Erickson, Abhinav Aggarwal, G. Matthew Fricke +1
Measurement of volcanic CO2 flux by a drone swarm poses special challenges. Drones must be able to follow gas concentration gradients while tolerating frequent drone loss. We prese…
On the Minimal Set of Inputs Required for Efficient Neuro-Evolved Foraging
John Erickson, Abhinav Aggarwal, Melanie E. Moses
In this paper, we perform an ablation study of \neatfa, a neuro-evolved foraging algorithm that has recently been shown to forage efficiently under different resource distributions…
A Most Irrational Foraging Algorithm
Abhinav Aggarwal, William F. Vining, Diksha Gupta +2
We present a foraging algorithm, GoldenFA, in which search direction is chosen based on the Golden Ratio. We show both theoretically and empirically that GoldenFA is more efficient…
Multithreaded Filtering Preconditioner for Diffusion Equation on Structured Grid
Abhinav Aggarwal, Shivam Kakkar, Pawan Kumar
A parallel and nested version of a frequency filtering preconditioner is proposed for linear systems corresponding to diffusion equation on a structured grid. The proposed precondi…
Paying Attention to Attention: Highlighting Influential Samples in Sequential Analysis
Cynthia Freeman, Jonathan Merriman, Abhinav Aggarwal +2
In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying t…
REMOTEGATE: Incentive-Compatible Remote Configuration of Security Gateways
Abhinav Aggarwal, Mahdi Zamani, Mihai Christodorescu
Imagine that a malicious hacker is trying to attack a server over the Internet and the server wants to block the attack packets as close to their point of origin as possible. Howev…
A similarity criterion for sequential programs using truth-preserving partial functions
Abhinav Aggarwal
The execution of sequential programs allows them to be represented using mathematical functions formed by the composition of statements following one after the other. Each such sta…
Beating the Multiplicative Weights Update Algorithm
Abhinav Aggarwal, José Abel Castellanos Joo, Diksha Gupta
Multiplicative weights update algorithms have been used extensively in designing iterative algorithms for many computational tasks. The core idea is to maintain a distribution over…
Distributed Computing with Channel Noise
Abhinav Aggarwal, Varsha Dani, Thomas P. Hayes +1
A group of users want to run a distributed protocol over a network where communication occurs via private point-to-point channels. Unfortunately, an adversary, who knows $π…
Sending a Message with Unknown Noise
Abhinav Aggarwal, Varsha Dani, Thomas Hayes +1
Alice and Bob are connected via a two-way channel, and Alice wants to send a message of bits to Bob. An adversary flips an arbitrary but finite number of bits, , on the chan…
Introduction to Functional Grammars
Abhinav Aggarwal
Formal grammars are extensively used in Computer Science and related fields to study the rules which govern production of a language. The use of these grammars can be extended beyo…
Algebraic Message Authentication Codes
Abhinav Aggarwal
This paper suggests a message authentication scheme, which can be efficiently used for secure digital signature creation. The algorithm used here is an adjusted union of the concep…
A theory of function-induced-orders to study recursion termination
Abhinav Aggarwal, Padam Kumar
Termination property of functions is an important issue in computability theory. In this paper, we show that repeated iterations of a function can induce an order amongst the eleme…