Skip to content

Publications & ideas

Research

Selected publications, research notes, and my doctoral thesis. The complete and current publication record is on Google Scholar .

27 entries

Auditing & robustness

Beyond the imitation game: Quantifying and extrapolating the capabilities of language models

Auditing & robustness

Auditing saliency cropping algorithms

Auditing & robustness

Model weight theft with just noise inputs: The curious case of the petulant attacker

Auditing & robustness

Understanding adversarial robustness through loss landscape geometries

Auditing & robustness

Vulnerability of deep learning-based gait biometric recognition to adversarial perturbations

Auditing & robustness

On Lyapunov exponents and adversarial perturbation

Auditing & robustness

On detecting adversarial inputs with entropy of saliency maps

Auditing & robustness

On grey-box adversarial attacks and transfer learning

Auditing & robustness

Art-attack! on style transfers with textures, label categories and adversarial examples

Auditing & robustness

SIMUni: Sampling Impostors from Misfit Universal Background Models in accelerometric gait biometric verification

Auditing & robustness

Smile in the face of adversity much? A print based spoofing attack

Auditing & robustness

OODles of ODDs: The landscape of Out-of-distribution vulnerabilities of vision models

Auditing & robustness

Did They Direct the Violence or Admonish It? A Cautionary Tale on Contronomy, Androcentrism and Back-Translation Foibles

Datasets & ethics

Multimodal datasets: misogyny, pornography, and malignant stereotypes

Datasets & ethics

Large image datasets: A pyrrhic win for computer vision?

Datasets & ethics

Into the laion’s den: Investigating hate in multimodal datasets

Datasets & ethics

On Hate Scaling Laws For Data-Swamps

Datasets & ethics

The blood diamond effect in neural art: On ethically troublesome images of the imagenet dataset

Datasets & ethics

Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance

Datasets & ethics

JFT-300M: The mystery box

Theory & inference

Network Aided Classification and Detection of Data

Theory & inference

Channel estimation

Theory & inference

Time-of-arrival estimation framework for vehicular OFDM systems

Theory & inference

Latent sentiment detection in online social networks

Theory & inference

Bipartisan cloture roll call vote prediction using the joint press release network in us senate

Theory & inference

Outage secrecy capacity analysis for wireless communications

Theory & inference

Filter design with secrecy constraints

These entries were linked from the original website. Titles and source links are retained; publication dates and venues are shown only where verified.

Ideas are better in conversation.

Research, collaborations, or a good question.

vinayup@gmail.com