arXiv subjects

Deval Pandya

Publications and source records attributed to Deval Pandya.

14 recordsLinked to original sources

arXiv2026

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

Textual Collaborative Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for large language models (LLMs) while keeping their data locally. Its reliance on free-form textual updating and aggregation introduces a new and largely unexplored attack surface, i.e., malicious instructions can be injected into local prompts and propagated through server-side prompt aggregation. Unlike conventional prompt injection attacks, attacking TCPO targets the collaborative optimization loop in TCPO. This setting is more challenging because malicious instructions must survive aggregation, persist through subsequent benign prompt optimization, and evade server-side defenses. To expose this risk, we propose Collaborative Prompt Injection (CPInj) attack that contaminates the aggregated global prompt with malicious instructions, degrades downstream task performance, resists purification by prompt optimization on benign clients, and evades advanced detection-based defenses on the server. We find that current defense methods are ineffective against CPInj. We further propose Anchored Purification Aggregation (APAgg), a defense-oriented aggregation that purifies malicious instructions without severely degrading TCPO utility. We conduct extensive experiments across three LLM families and five reasoning tasks in math, logic, and medicine, and demonstrate that our proposed attack reveals a critical vulnerability in TCPO. Although we take a first step toward mitigation, the attack remains highly effective and far from fully resolved, calling for more robust defense for TCPO.

cs.CR↗

arXiv2026

MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data

Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative models like diffusion models, synthetic data is expected to preserve the statistical properties of the original dataset while remaining resilient to privacy attacks. Recent developments of diffusion models have been effective on a wide range of data types, but their privacy resilience, particularly for tabular formats, remains largely unexplored. MIDST challenge sought a quantitative evaluation of the privacy gain of synthetic tabular data generated by diffusion models, with a specific focus on its resistance to membership inference attacks (MIAs). Given the heterogeneity and complexity of tabular data, multiple target models were explored for MIAs, including diffusion models for single tables of mixed data types and multi-relational tables with interconnected constraints. MIDST inspired the development of novel black-box and white-box MIAs tailored to these target diffusion models as a key outcome, enabling a comprehensive evaluation of their privacy efficacy. The MIDST GitHub repository is available at https://github.com/VectorInstitute/MIDST

cs.LG↗

arXiv2026

RVCBench: Benchmarking the Robustness of Voice Cloning Across Modern Audio Generation Models

Modern voice cloning, also known as zero-shot text-to-speech (TTS), can synthesize speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized speech interfaces and dubbing. In practice, these systems often face noisy reference audio, imperfect text prompts, multilingual and long-form generation, post-processing, and adversarial perturbations, all of which can weaken robustness. Despite rapid progress in codec-token language models and diffusion-based TTS, robustness under realistic deployment shifts remains underexplored. This paper introduces RVCBench, a comprehensive dataset and benchmark for evaluating robustness in voice cloning. RVCBench provides task-aligned tests covering controlled text-audio pairing, multilingual and long-form scenarios, expressive prompts, post-processing conditions, and passive or proactive audio perturbations. Across 18 robustness evaluations, 225 speakers, and 14,370 utterances, RVCBench supports unified evaluation of input sensitivity, generation stability, output resilience, perturbation robustness, speaker similarity, and deepfake detectability. We evaluate 18 representative open-source voice cloning models and reveal systematic vulnerabilities in content consistency, speaker similarity, long-form stability, post-processing resilience, adversarial robustness, and detector-facing separability. We release the code and dataset to support reproducible evaluation and future research on robust voice cloning, speech synthesis, and audio generation. Code: https://github.com/Nanboy-Ronan/RVCBench. Dataset: https://huggingface.co/datasets/Nanboy/RVCBench.

cs.SD↗

arXiv2026

Position: Sustainable Open-Source AI Requires Tracking the Cumulative Footprint of Derivatives

Open-source AI is scaling rapidly, and model hubs now host millions of artifacts. Each foundation model can spawn large numbers of fine-tunes, adapters, quantizations, merges, and forks. We take the position that compute efficiency alone is insufficient for sustainability in open-source AI. Lower per-run costs can accelerate experimentation and deployment, increasing aggregate footprint unless impacts are measurable and comparable across derivative lineages. However, the energy use, water consumption, and emissions of these derivative lineages are rarely measured or disclosed in a consistent, comparable way, leaving aggregate ecosystem impact largely invisible. We argue that sustainable open-source AI requires a coordination infrastructure that tracks impacts across model lineages, not only base models. We propose Data and Impact Accounting (DIA), a lightweight, non-restrictive transparency layer that (i) standardizes carbon-and-water reporting metadata, (ii) integrates low-friction measurement into common training and inference pipelines, and (iii) aggregates reports via public dashboards to summarize cumulative impacts across releases and derivatives. DIA makes derivative costs visible and supports ecosystem-level accountability while preserving openness. Project Page: https://vectorinstitute.github.io/ai-impact-accounting/

cs.ET↗

arXiv2026

SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding

Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process sequential audio-video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting. We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of 60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summarization, multiple-choice question (MCQ) answering, and temporal localization with supporting rationales (reasoning). Across closed- and open-source models, we find that the MCQ accuracy shows the smallest gap between model families, but the best closed-source model outperforms the best open-source model by 22.6% on temporal localization. We further observe accuracy gaps of up to 21.4% on temporal localization across demographic groups, indicating persistent disparities in model behaviour. SONIC-O1 provides an open evaluation suite for temporally grounded and demographically robust multimodal understanding. SONIC-O1 is publicly available for research: Project page (https://vectorinstitute.github.io/sonic-o1/), Dataset (https://huggingface.co/datasets/vector-institute/sonic-o1), GitHub (https://github.com/vectorinstitute/sonic-o1), Leaderboard (https://huggingface.co/spaces/vector-institute/sonic-o1-leaderboard).

cs.AI↗

arXiv2025

Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods

Large language models (LLMs) reproduce misinformation not by memorizing false facts alone, but by learning the linguistic patterns that make falsehoods persuasive, such as hedging, false presuppositions, and fabricated citations. We propose model immunization, a training paradigm based on supervised fine-tuning over curated (false claim, correction) pairs, injected as small vaccine doses (5 to 10% of tokens) alongside truthful data. Unlike post-hoc filtering or preference-based alignment, immunization introduces direct negative supervision on labeled falsehoods. Across four open weight model families, this approach improves TruthfulQA accuracy by 12 points and increases misinformation rejection rates by 30 points, while preserving overall model capability. We further outline key design requirements, including dosage, labeling, quarantine, and diversity and advocate for standardized vaccine corpora and benchmarks to evaluate generalization. These findings position immunization as a practical and scalable component of responsible LLM development.

cs.CL↗

arXiv2025

HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation

Although recent large multimodal models (LMMs) show impressive progress on vision language tasks, their alignment with human centered (HC) principles such as fairness, ethics, inclusivity, empathy, and robustness is often overlooked. Existing LMM benchmarks are largely accuracy-agnostic. We present HumaniBench, a unified framework for characterizing HC alignment across realistic, socially grounded visual contexts. It contains 32,000 expert-verified image-question pairs from real-world news imagery, each mapped to one or more HC principles through explicit metrics. Comparing 15 state of the art LMMs reveals consistent trade -offs: proprietary systems lead on ethics, reasoning, and empathy, while open-source models show superior visual grounding and resilience. All models show persistent gaps in fairness and multilingual inclusivity. Chain-of-thought prompting and test-time scaling yield 8to 12 % gains on several HC dimensions. HumaniBench enables fine-grained analysis of alignment trade-offs not captured by conventional multimodal benchmarks. https://vectorinstitute.github.io/humanibench/

cs.CV↗

arXiv2024

Practical Guide for Causal Pathways and Sub-group Disparity Analysis

In this study, we introduce the application of causal disparity analysis to unveil intricate relationships and causal pathways between sensitive attributes and the targeted outcomes within real-world observational data. Our methodology involves employing causal decomposition analysis to quantify and examine the causal interplay between sensitive attributes and outcomes. We also emphasize the significance of integrating heterogeneity assessment in causal disparity analysis to gain deeper insights into the impact of sensitive attributes within specific sub-groups on outcomes. Our two-step investigation focuses on datasets where race serves as the sensitive attribute. The results on two datasets indicate the benefit of leveraging causal analysis and heterogeneity assessment not only for quantifying biases in the data but also for disentangling their influences on outcomes. We demonstrate that the sub-groups identified by our approach to be affected the most by disparities are the ones with the largest ML classification errors. We also show that grouping the data only based on a sensitive attribute is not enough, and through these analyses, we can find sub-groups that are directly affected by disparities. We hope that our findings will encourage the adoption of such methodologies in future ethical AI practices and bias audits, fostering a more equitable and fair technological landscape.

cs.CY↗

arXiv2024

FAIIR: Building Toward A Conversational AI Agent Assistant for Youth Mental Health Service Provision

The world's healthcare systems and mental health agencies face both a growing demand for youth mental health services, alongside a simultaneous challenge of limited resources. Here, we focus on frontline crisis support, where Crisis Responders (CRs) engage in conversations for youth mental health support and assign an issue tag to each conversation. In this study, we develop FAIIR (Frontline Assistant: Issue Identification and Recommendation), an advanced tool leveraging an ensemble of domain-adapted and fine-tuned transformer models trained on a large conversational dataset comprising 780,000 conversations. The primary aim is to reduce the cognitive burden on CRs, enhance the accuracy of issue identification, and streamline post-conversation administrative tasks. We evaluate FAIIR on both retrospective and prospective conversations, emphasizing human-in-the-loop design with active CR engagement for model refinement, consensus-building, and overall assessment. Our results indicate that FAIIR achieves an average AUCROC of 94%, a sample average F1-score of 64%, and a sample average recall score of 81% on the retrospective test set. We also demonstrate the robustness and generalizability of the FAIIR tool during the silent testing phase, with less than a 2% drop in all performance metrics. Notably, CRs' responses exhibited an overall agreement of 90.9% with FAIIR's predictions. Furthermore, expert agreement with FAIIR surpassed their agreement with the original labels. To conclude, our findings indicate that assisting with the identification of issues of relevance helps reduce the burden on CRs, ensuring that appropriate resources can be provided and that active rescues and mandatory reporting can take place in critical situations requiring immediate de-escalation.

cs.AI↗

arXiv2024

FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?

The rapid evolution of Large Language Models (LLMs) highlights the necessity for ethical considerations and data integrity in AI development, particularly emphasizing the role of FAIR (Findable, Accessible, Interoperable, Reusable) data principles. While these principles are crucial for ethical data stewardship, their specific application in the context of LLM training data remains an under-explored area. This research gap is the focus of our study, which begins with an examination of existing literature to underline the importance of FAIR principles in managing data for LLM training. Building upon this, we propose a novel framework designed to integrate FAIR principles into the LLM development lifecycle. A contribution of our work is the development of a comprehensive checklist intended to guide researchers and developers in applying FAIR data principles consistently across the model development process. The utility and effectiveness of our framework are validated through a case study on creating a FAIR-compliant dataset aimed at detecting and mitigating biases in LLMs. We present this framework to the community as a tool to foster the creation of technologically advanced, ethically grounded, and socially responsible AI models.

cs.CL↗

arXiv2023

Mitigating Bias in Conversations: A Hate Speech Classifier and Debiaser with Prompts

Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an approach that involves a two-step process: first, detecting hate speech using a classifier, and then utilizing a debiasing component that generates less biased or unbiased alternatives through prompts. We evaluated our approach on a benchmark dataset and observed reduction in negativity due to hate speech comments. The proposed method contributes to the ongoing efforts to reduce biases in online discourse and promote a more inclusive and fair environment for communication.

cs.CL↗

arXiv2023

Soft-prompt Tuning for Large Language Models to Evaluate Bias

Prompting large language models has gained immense popularity in recent years due to the advantage of producing good results even without the need for labelled data. However, this requires prompt tuning to get optimal prompts that lead to better model performances. In this paper, we explore the use of soft-prompt tuning on sentiment classification task to quantify the biases of large language models (LLMs) such as Open Pre-trained Transformers (OPT) and Galactica language model. Since these models are trained on real-world data that could be prone to bias toward certain groups of populations, it is important to identify these underlying issues. Using soft-prompts to evaluate bias gives us the extra advantage of avoiding the human-bias injection that can be caused by manually designed prompts. We check the model biases on different sensitive attributes using the group fairness (bias) and find interesting bias patterns. Since LLMs have been used in the industry in various applications, it is crucial to identify the biases before deploying these models in practice. We open-source our pipeline and encourage industry researchers to adapt our work to their use cases.

cs.CL↗

arXiv2023

MLHOps: Machine Learning for Healthcare Operations

Machine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in healthcare settings. This paper provides both a survey of work in this area and guidelines for developers and clinicians to deploy and maintain their own models in clinical practice. We cover the foundational concepts of general machine learning operations, describe the initial setup of MLHOps pipelines (including data sources, preparation, engineering, and tools). We then describe long-term monitoring and updating (including data distribution shifts and model updating) and ethical considerations (including bias, fairness, interpretability, and privacy). This work therefore provides guidance across the full pipeline of MLHOps from conception to initial and ongoing deployment.

cs.LG↗

arXiv2023

Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support

Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natural Language Processing (NLP) technology. We combine expertise from academia and industry to bridge the gap and build task/domain-specific Neural Agent Assistants (NAA) with three high-level components for: (1) Intent Identification, (2) Context Retrieval, and (3) Response Generation. In this paper, we outline the pipeline of the NAA's core system and also present three case studies in which three industry partners successfully adapt the framework to find solutions to their unique challenges. Our findings suggest that a collaborative process is instrumental in spurring the development of emerging NLP models for Conversational AI tasks in industry. The full reference implementation code and results are available at \url{https://github.com/VectorInstitute/NAA}

cs.CL↗