arXiv subjects

Krishna P. Gummadi

Publications and source records attributed to Krishna P. Gummadi.

At least 37 records · Page 2Linked to original sources

arXiv2026

Does Ad-Free Mean Less Data Collection? An Empirical Study of Platform Data Practices and User Expectations

Online platforms increasingly offer "paid" ad-free subscriptions as an alternative to the traditional "free" ad-based model. The transition to ad-free models ostensibly removes advertising as a key justification for data processing under the GDPR. So, normatively, platforms should collect less user data. However, platforms may justify continued data collection as a means to provide an improved, personalized experience. This tension between privacy principles and platform incentives raises a critical underexplored question: do data collection practices vary between ad-free and ad-based subscription models? In this paper, we shed light on this important privacy issue by investigating the alignment between platform data collection practices and related user expectations. With respect to data collection process, our analyses of data exports from three major online platforms - Instagram, Facebook, and X - reveal that these platforms continue to retain or collect some ad-related data, even in ad-free subscriptions. With respect to user expectations, our survey among 255 participants on Prolific reveals that 69% of the participants normatively expect data collection to be reduced, indicating their expectation of improved digital privacy in an ad-free model. However, when asked what they think actually happens, 63% of these participants believed that platforms would still collect about the same amount of data, highlighting skepticism about platform practices. Our findings not only indicate a significant disconnect between data practices and normative user expectations, but also raise serious questions about platform compliance with core GDPR principles, such as purpose limitation, data minimization, and transparency.

cs.CY↗

arXiv2025

Hubble: a Model Suite to Advance the Study of LLM Memorization

We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English corpus, and perturbed models are trained in the same way but with controlled insertion of text (e.g., book passages, biographies, and test sets) designed to emulate key memorization risks. Our core release includes 8 models -- standard and perturbed models with 1B or 8B parameters, pretrained on 100B or 500B tokens -- establishing that memorization risks are determined by the frequency of sensitive data relative to size of the training corpus (i.e., a password appearing once in a smaller corpus is memorized better than the same password in a larger corpus). Our release also includes 6 perturbed models with text inserted at different pretraining phases, showing that sensitive data without continued exposure can be forgotten. These findings suggest two best practices for addressing memorization risks: to dilute sensitive data by increasing the size of the training corpus, and to order sensitive data to appear earlier in training. Beyond these general empirical findings, Hubble enables a broad range of memorization research; for example, analyzing the biographies reveals how readily different types of private information are memorized. We also demonstrate that the randomized insertions in Hubble make it an ideal testbed for membership inference and machine unlearning, and invite the community to further explore, benchmark, and build upon our work.

cs.CL↗

arXiv2025

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability

Understanding the relationship between training data and model behavior during pretraining is crucial, but existing workflows make this process cumbersome, fragmented, and often inaccessible to researchers. We present TokenSmith, an open-source library for interactive editing, inspection, and analysis of datasets used in Megatron-style pretraining frameworks such as GPT-NeoX, Megatron, and NVIDIA NeMo. TokenSmith supports a wide range of operations including searching, viewing, ingesting, exporting, inspecting, and sampling data, all accessible through a simple user interface and a modular backend. It also enables structured editing of pretraining data without requiring changes to training code, simplifying dataset debugging, validation, and experimentation. TokenSmith is designed as a plug-and-play addition to existing large language model pretraining workflows, thereby democratizing access to production-grade dataset tooling. TokenSmith is hosted on GitHub, with accompanying documentation, tutorials, and a demonstration video (available on YouTube).

cs.CL↗

arXiv2025

Understanding Blockchain Governance: Analyzing Decentralized Voting to Amend DeFi Smart Contracts

Decentralized Autonomous Organizations (DAOs) have emerged as a novel governance mechanism in blockchain ecosystems, particularly within Decentralized Finance (DeFi). By enabling token holders to propose and vote on protocol changes, these systems promise transparent and equitable decision-making without centralized control. In this paper, we present an in-depth empirical study of the governance protocols of Compound and Uniswap, two of the most widely used DAOs in DeFi. Analyzing over 370 governance proposals and millions of on-chain events from their inception until August 2024, we uncover significant centralization of voting power: as few as 3--5 voters were sufficient to sway the majority of proposals. We also find that the cost of voting disproportionately burdens smaller token holders, and that strategic voting behaviors, such as delayed participation and coalition formation, further distort governance outcomes. Our findings suggest that despite their decentralized ideals, current DAO governance mechanisms fall short in practice.

cs.CR↗

arXiv2025

Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity

Machine learning (ML) algorithms can often exhibit discriminatory behavior, negatively affecting certain populations across protected groups. To address this, numerous debiasing methods, and consequently evaluation measures, have been proposed. Current evaluation measures for debiasing methods suffer from two main limitations: (1) they primarily provide a global estimate of unfairness, failing to provide a more fine-grained analysis, and (2) they predominantly analyze the model output on a specific task, failing to generalize the findings to other tasks. In this work, we introduce Pointwise Normalized Kernel Alignment (PNKA), a pointwise representational similarity measure that addresses these limitations by measuring how debiasing measures affect the intermediate representations of individuals. On tabular data, the use of PNKA reveals previously unknown insights: while group fairness predominantly influences a small subset of the population, maintaining high representational similarity for the majority, individual fairness constraints uniformly impact representations across the entire population, altering nearly every data point. We show that by evaluating representations using PNKA, we can reliably predict the behavior of ML models trained on these representations. Moreover, applying PNKA to language embeddings shows that existing debiasing methods may not perform as intended, failing to remove biases from stereotypical words and sentences. Our findings suggest that current evaluation measures for debiasing methods are insufficient, highlighting the need for a deeper understanding of the effects of debiasing methods, and show how pointwise representational similarity metrics can help with fairness audits.

cs.LG↗

arXiv2025

Studying Behavioral Addiction by Combining Surveys and Digital Traces: A Case Study of TikTok

Opaque algorithms disseminate and mediate the content that users consume on online social media platforms. This algorithmic mediation serves users with contents of their liking, on the other hand, it may cause several inadvertent risks to society at scale. While some of these risks, e.g., filter bubbles or dissemination of hateful content, are well studied in the community, behavioral addiction, designated by the Digital Services Act (DSA) as a potential systemic risk, has been understudied. In this work, we aim to study if one can effectively diagnose behavioral addiction using digital data traces from social media platforms. Focusing on the TikTok short-format video platform as a case study, we employ a novel mixed methodology of combining survey responses with data donations of behavioral traces. We survey 1590 TikTok users and stratify them into three addiction groups (i.e., less/moderately/highly likely addicted). Then, we obtain data donations from 107 surveyed participants. By analyzing users' data we find that, among others, highly likely addicted users spend more time watching TikTok videos and keep coming back to TikTok throughout the day, indicating a compulsion to use the platform. Finally, by using basic user engagement features, we train classifier models to identify highly likely addicted users with $F_1 \geq 0.55$. The performance of the classifier models suggests predicting addictive users solely based on their usage is rather difficult.

cs.SI↗

arXiv2024

Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction

In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with prior approaches, we propose to eliminate prompt engineering when probing LLMs for factual knowledge. Our approach, called Zero-Prompt Latent Knowledge Estimator (ZP-LKE), leverages the in-context learning ability of LLMs to communicate both the factual knowledge question as well as the expected answer format. Our knowledge estimator is both conceptually simpler (i.e., doesn't depend on meta-linguistic judgments of LLMs) and easier to apply (i.e., is not LLM-specific), and we demonstrate that it can surface more of the latent knowledge embedded in LLMs. We also investigate how different design choices affect the performance of ZP-LKE. Using the proposed estimator, we perform a large-scale evaluation of the factual knowledge of a variety of open-source LLMs, like OPT, Pythia, Llama(2), Mistral, Gemma, etc. over a large set of relations and facts from the Wikidata knowledge base. We observe differences in the factual knowledge between different model families and models of different sizes, that some relations are consistently better known than others but that models differ in the precise facts they know, and differences in the knowledge of base models and their finetuned counterparts. Code available at: https://github.com/QinyuanWu0710/ZeroPrompt_LKE

cs.CL↗

arXiv2024

Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications

Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and disentangle memorisation from other phenomena (e.g. in-context learning), we create an experimental framework that is based on repeatedly exposing LLMs to random strings. Our framework allows us to better understand the dynamics, i.e., the behaviour of the model, when repeatedly exposing it to random strings. Using our framework, we make several striking observations: (a) we find consistent phases of the dynamics across families of models (Pythia, Phi and Llama2), (b) we identify factors that make some strings easier to memorise than others, and (c) we identify the role of local prefixes and global context in memorisation. We also show that sequential exposition to different random strings has a significant effect on memorisation. Our results, often surprising, have significant downstream implications in the study and usage of LLMs.

cs.CL↗

arXiv2024

(De)Noise: Moderating the Inconsistency Between Human Decision-Makers

Prior research in psychology has found that people's decisions are often inconsistent. An individual's decisions vary across time, and decisions vary even more across people. Inconsistencies have been identified not only in subjective matters, like matters of taste, but also in settings one might expect to be more objective, such as sentencing, job performance evaluations, or real estate appraisals. In our study, we explore whether algorithmic decision aids can be used to moderate the degree of inconsistency in human decision-making in the context of real estate appraisal. In a large-scale human-subject experiment, we study how different forms of algorithmic assistance influence the way that people review and update their estimates of real estate prices. We find that both (i) asking respondents to review their estimates in a series of algorithmically chosen pairwise comparisons and (ii) providing respondents with traditional machine advice are effective strategies for influencing human responses. Compared to simply reviewing initial estimates one by one, the aforementioned strategies lead to (i) a higher propensity to update initial estimates, (ii) a higher accuracy of post-review estimates, and (iii) a higher degree of consistency between the post-review estimates of different respondents. While these effects are more pronounced with traditional machine advice, the approach of reviewing algorithmically chosen pairs can be implemented in a wider range of settings, since it does not require access to ground truth data.

cs.HC↗

arXiv2024

Understanding the Role of Invariance in Transfer Learning

Transfer learning is a powerful technique for knowledge-sharing between different tasks. Recent work has found that the representations of models with certain invariances, such as to adversarial input perturbations, achieve higher performance on downstream tasks. These findings suggest that invariance may be an important property in the context of transfer learning. However, the relationship of invariance with transfer performance is not fully understood yet and a number of questions remain. For instance, how important is invariance compared to other factors of the pretraining task? How transferable is learned invariance? In this work, we systematically investigate the importance of representational invariance for transfer learning, as well as how it interacts with other parameters during pretraining. To do so, we introduce a family of synthetic datasets that allow us to precisely control factors of variation both in training and test data. Using these datasets, we a) show that for learning representations with high transfer performance, invariance to the right transformations is as, or often more, important than most other factors such as the number of training samples, the model architecture and the identity of the pretraining classes, b) show conditions under which invariance can harm the ability to transfer representations and c) explore how transferable invariance is between tasks. The code is available at \url{https://github.com/tillspeicher/representation-invariance-transfer}.

cs.LG↗

arXiv2024

Investigating Nudges toward Related Sellers on E-commerce Marketplaces: A Case Study on Amazon

E-commerce marketplaces provide business opportunities to millions of sellers worldwide. Some of these sellers have special relationships with the marketplace by virtue of using their subsidiary services (e.g., fulfillment and/or shipping services provided by the marketplace) -- we refer to such sellers collectively as Related Sellers. When multiple sellers offer to sell the same product, the marketplace helps a customer in selecting an offer (by a seller) through (a) a default offer selection algorithm, (b) showing features about each of the offers and the corresponding sellers (price, seller performance metrics, seller's number of ratings etc.), and (c) finally evaluating the sellers along these features. In this paper, we perform an end-to-end investigation into how the above apparatus can nudge customers toward the Related Sellers on Amazon's four different marketplaces in India, USA, Germany and France. We find that given explicit choices, customers' preferred offers and algorithmically selected offers can be significantly different. We highlight that Amazon is adopting different performance metric evaluation policies for different sellers, potentially benefiting Related Sellers. For instance, such policies result in notable discrepancy between the actual performance metric and the presented performance metric of Related Sellers. We further observe that among the seller-centric features visible to customers, sellers' number of ratings influences their decisions the most, yet it may not reflect the true quality of service by the seller, rather reflecting the scale at which the seller operates, thereby implicitly steering customers toward larger Related Sellers. Moreover, when customers are shown the rectified metrics for the different sellers, their preference toward Related Sellers is almost halved.

cs.CY↗

arXiv2024

Antitrust, Amazon, and Algorithmic Auditing

In digital markets, antitrust law and special regulations aim to ensure that markets remain competitive despite the dominating role that digital platforms play today in everyone's life. Unlike traditional markets, market participant behavior is easily observable in these markets. We present a series of empirical investigations into the extent to which Amazon engages in practices that are typically described as self-preferencing. We discuss how the computer science tools used in this paper can be used in a regulatory environment that is based on algorithmic auditing and requires regulating digital markets at scale.

cs.CY↗

arXiv2024

Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations

Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation systems that offer endless streams of such content. In this work, we analyze user engagement on TikTok using data we collect via a data donation system that allows TikTok users to donate their data. We recruited 347 TikTok users and collected 9.2M TikTok video recommendations they received. By analyzing user engagement, we find that the average daily usage time increases over the users' lifetime while the user attention remains stable at around 45%. We also find that users like more videos uploaded by people they follow than those recommended by people they do not follow. Our study offers valuable insights into how users engage with short-format videos on TikTok and lessons learned from designing a data donation system.

cs.SI↗

arXiv2024

TikTok and the Art of Personalization: Investigating Exploration and Exploitation on Social Media Feeds

Recommendation algorithms for social media feeds often function as black boxes from the perspective of users. We aim to detect whether social media feed recommendations are personalized to users, and to characterize the factors contributing to personalization in these feeds. We introduce a general framework to examine a set of social media feed recommendations for a user as a timeline. We label items in the timeline as the result of exploration vs. exploitation of the user's interests on the part of the recommendation algorithm and introduce a set of metrics to capture the extent of personalization across user timelines. We apply our framework to a real TikTok dataset and validate our results using a baseline generated from automated TikTok bots, as well as a randomized baseline. We also investigate the extent to which factors such as video viewing duration, liking, and following drive the personalization of content on TikTok. Our results demonstrate that our framework produces intuitive and explainable results, and can be used to audit and understand personalization in social media feeds.

cs.SI↗

arXiv2023

Diffused Redundancy in Pre-trained Representations

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a given layer exhibit a degree of diffuse redundancy, ie, any randomly chosen subset of neurons in the layer that is larger than a threshold size shares a large degree of similarity with the full layer and is able to perform similarly as the whole layer on a variety of downstream tasks. For example, a linear probe trained on $20\%$ of randomly picked neurons from the penultimate layer of a ResNet50 pre-trained on ImageNet1k achieves an accuracy within $5\%$ of a linear probe trained on the full layer of neurons for downstream CIFAR10 classification. We conduct experiments on different neural architectures (including CNNs and Transformers) pre-trained on both ImageNet1k and ImageNet21k and evaluate a variety of downstream tasks taken from the VTAB benchmark. We find that the loss and dataset used during pre-training largely govern the degree of diffuse redundancy and the "critical mass" of neurons needed often depends on the downstream task, suggesting that there is a task-inherent redundancy-performance Pareto frontier. Our findings shed light on the nature of representations learned by pre-trained deep neural networks and suggest that entire layers might not be necessary to perform many downstream tasks. We investigate the potential for exploiting this redundancy to achieve efficient generalization for downstream tasks and also draw caution to certain possible unintended consequences. Our code is available at \url{https://github.com/nvedant07/diffused-redundancy}.

cs.LG↗

arXiv2023

Dissecting Bitcoin and Ethereum Transactions: On the Lack of Transaction Contention and Prioritization Transparency in Blockchains

In permissionless blockchains, transaction issuers include a fee to incentivize miners to include their transactions. To accurately estimate this prioritization fee for a transaction, transaction issuers (or blockchain participants, more generally) rely on two fundamental notions of transparency, namely contention and prioritization transparency. Contention transparency implies that participants are aware of every pending transaction that will contend with a given transaction for inclusion. Prioritization transparency states that the participants are aware of the transaction or prioritization fees paid by every such contending transaction. Neither of these notions of transparency holds well today. Private relay networks, for instance, allow users to send transactions privately to miners. Besides, users can offer fees to miners via either direct transfers to miners' wallets or off-chain payments -- neither of which are public. In this work, we characterize the lack of contention and prioritization transparency in Bitcoin and Ethereum resulting from such practices. We show that private relay networks are widely used and private transactions are quite prevalent. We show that the lack of transparency facilitates miners to collude and overcharge users who may use these private relay networks despite them offering little to no guarantees on transaction prioritization. The lack of these transparencies in blockchains has crucial implications for transaction issuers as well as the stability of blockchains. Finally, we make our data sets and scripts publicly available.

cs.CR↗

arXiv2022

Do Invariances in Deep Neural Networks Align with Human Perception?

An evaluation criterion for safe and trustworthy deep learning is how well the invariances captured by representations of deep neural networks (DNNs) are shared with humans. We identify challenges in measuring these invariances. Prior works used gradient-based methods to generate identically represented inputs (IRIs), ie, inputs which have identical representations (on a given layer) of a neural network, and thus capture invariances of a given network. One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans. Prior works, however, have mixed takeaways; some argue that later layers of DNNs do not learn human-like invariances (\cite{jenelle2019metamers}) yet others seem to indicate otherwise (\cite{mahendran2014understanding}). We argue that the loss function used to generate IRIs can heavily affect takeaways about invariances of the network and is the primary reason for these conflicting findings. We propose an adversarial regularizer on the IRI generation loss that finds IRIs that make any model appear to have very little shared invariance with humans. Based on this evidence, we argue that there is scope for improving models to have human-like invariances, and further, to have meaningful comparisons between models one should use IRIs generated using the regularizer-free loss. We then conduct an in-depth investigation of how different components (eg architectures, training losses, data augmentations) of the deep learning pipeline contribute to learning models that have good alignment with humans. We find that architectures with residual connections trained using a (self-supervised) contrastive loss with $\ell_p$ ball adversarial data augmentation tend to learn invariances that are most aligned with humans. Code: \url{github.com/nvedant07/Human-NN-Alignment}.

cs.CV↗