arXiv subjects

Aritra Dasgupta

Publications and source records attributed to Aritra Dasgupta.

At least 19 recordsLinked to original sources

arXiv2026

Relevance is not enough: A Communication-Oriented Retrieval System for Consequential Scientific Question Answering

AI systems increasingly answer scientific questions about health, safety, and the environment. But most retrieval-augmented generation systems are tuned to provide factually correct, on-topic answers rather than to help non-experts understand what those answers mean for their lives and decisions. We focus on consequential scientific questions whose results directly shape people's lives and study them through a public water-quality communication system, where residents and community leaders interpret the findings and choose actions. Their experiences show that on-topic answers can still be insufficient without explanation and context and that the emotional weight of risk information cannot be ignored. Our system first classifies each question by reasoning type (for example, causal versus policy-based), then generates follow-up questions to identify missing evidence and retrieve it. One component clearly distinguishes between what is known and what is uncertain, while another rewrites scientific details into accessible language, using persona-based styles, such as a caring neighbor or an administrative official, to adapt tone and readability. Ablations on over $160$ questions show that the system uses $\textit{an order of magnitude less context}$ and, in several configurations, improves human-rated completeness. A completeness metric co-designed with community members and a fine-tuned learned judge reveal that standard relevance scores explain about $1\%$ of variation in human completeness ratings, and even the tuned judge only moderately aligns with humans, indicating that completeness is a distinct human-centered objective that current metrics do not reliably capture.

cs.IR↗

arXiv2026

Lessons from the Hardware Hacking Competitions: Verification Techniques, Findings, and Insights

Hardware hacking competitions have emerged as practical platforms for evaluating security weaknesses in complex System-on-Chip (SoC) designs while promoting security-aware verification and tool development. This paper presents a systematic study of SoC security verification through open-box hardware hacking competitions, focusing on practical vulnerability analysis strategies, observed findings, and lessons for security-aware verification. We present a multi-strategy vulnerability analysis methodology, combining simulation-based verification, formal verification, lint analysis, Large Language Model (LLM)-assisted bug detection, and coverage-guided hybrid fuzzing. Representative vulnerability findings are analyzed to illustrate how different techniques expose complementary classes of security flaws, and we derive practical lessons for pre-silicon security verification. Finally, we discuss how competition benchmarks can support the reproducible evaluation of emerging hardware security techniques and guide future security-aware EDA research.

cs.CR↗

arXiv2026

A Multimodal Reasoning Typology for Grounding Chart-Image Coherence in Science Communication

Charts and images appear together throughout scientific publications, yet most computational work does not characterize their coherence. We argue that a chart, its accompanying image, and the caption that links them form a multimodal unit, and that the inferential work required to read it varies systematically. To capture this variation, we develop a typology of reasoning gaps, R1 through R5, that characterizes how chart, image, and text jointly convey a scientific claim, and the interpretive work this demands of the reader. Some pairs restate the same data, while in other pairs, charts are used to quantify a structure the image localizes, project image content onto an external variable, audit an image-based claim, or jointly construct a frame that neither panel can establish alone. The typology is anchored in the grounding theory of communication and was derived bottom-up, with a neuroscience expert, from a corpus of 79 traumatic brain injury papers and 32 chart-image pairs. Crucially, the levels provide a systematic mechanism for identifying where grounding succeeds or breaks down, rather than leaving it to subjective inference. We show this in a study in which a domain expert and three non-experts judge vision-language model (VLM) descriptions of 25 pairs: the level predicts where their judgments align and where they diverge, isolating the points at which contextual knowledge, not the figure, carries coherence. This typology thus offers figure designers a systematic way to balance text against chart-image pairs, bridging the expert-to-non-expert divide in reading a scientific takeaway.

cs.CV↗

arXiv2026

Rationalize: Shared Semantic Reasoning for Human-AI Alignment

We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches.

cs.HC↗

arXiv2026

CIPHR: Cryptography Inspired IP Protection through Fine-Grain Hardware Redaction

Hardware intellectual property (IP) in the globalized integrated circuit (IC) supply chain is exposed to a wide range of confidentiality and integrity attacks by untrusted third-party entities. Existing IP-level countermeasures, such as logic locking, hardware obfuscation, camouflaging, and redaction, have aimed at addressing these them. In particular, hardware redaction has emerged as a robust approach for IP protection against confidentiality attacks, including reverse engineering. We note that existing IP protection approaches, including the ones based on hardware redaction, tend to leave behind structural artifacts that can be exploited by adversaries to bypass protections or predict unlocking keys, using the knowledge of known designs, akin to a known-plaintext attack (KPA) in cryptography. In this work, we present CIPHR, a robust fine-grain hardware redaction methodology inspired by the cryptographic property of indistinguishability. The proposed approach utilizes novel heuristic-driven randomization to introduce significant structural transformations into the redacted designs. We employ structural analysis metrics to evaluate the security achieved by CIPHR compared to various state-of-the-art IP protection techniques. Multiple open-source benchmark designs are used to demonstrate that fine-grain redaction in CIPHR is robust, scalable, and indistinguishable against structural attacks.

cs.CR↗

arXiv2026

Intelligent Graybox Fuzzing via ATPG-Guided Seed Generation and Submodule Analysis

Hardware Fuzzing emerged as one of the crucial techniques for finding security flaws in modern hardware designs by testing a wide range of input scenarios. One of the main challenges is creating high-quality input seeds that maximize coverage and speed up verification. Coverage-Guided Fuzzing (CGF) methods help explore designs more effectively, but they struggle to focus on specific parts of the hardware. Existing Directed Gray-box Fuzzing (DGF) techniques like DirectFuzz try to solve this by generating targeted tests, but it has major drawbacks, such as supporting only limited hardware description languages, not scaling well to large circuits, and having issues with abstraction mismatches. To address these problems, we introduce a novel framework, PROFUZZ, that follows the DGF approach and combines fuzzing with Automatic Test Pattern Generation (ATPG) for more efficient fuzzing. By leveraging ATPG's structural analysis capabilities, PROFUZZ can generate precise input seeds that target specific design regions more effectively while maintaining high fuzzing throughput. Our experiments show that PROFUZZ scales 30x better than DirectFuzz when handling multiple target sites, improves coverage by 11.66%, and runs 2.76x faster, highlighting its scalability and effectiveness for directed fuzzing in complex hardware systems.

cs.CR↗

arXiv2025

SynFuzz: Leveraging Fuzzing of Netlist to Detect Synthesis Bugs

In the evolving landscape of integrated circuit (IC) design, the increasing complexity of modern processors and intellectual property (IP) cores has introduced new challenges in ensuring design correctness and security. The recent advancements in hardware fuzzing techniques have shown their efficacy in detecting hardware bugs and vulnerabilities at the RTL abstraction level of hardware. However, they suffer from several limitations, including an inability to address vulnerabilities introduced during synthesis and gate-level transformations. These methods often fail to detect issues arising from library adversaries, where compromised or malicious library components can introduce backdoors or unintended behaviors into the design. In this paper, we present a novel hardware fuzzer, SynFuzz, designed to overcome the limitations of existing hardware fuzzing frameworks. SynFuzz focuses on fuzzing hardware at the gate-level netlist to identify synthesis bugs and vulnerabilities that arise during the transition from RTL to the gate-level. We analyze the intrinsic hardware behaviors using coverage metrics specifically tailored for the gate-level. Furthermore, SynFuzz implements differential fuzzing to uncover bugs associated with EDA libraries. We evaluated SynFuzz on popular open-source processors and IP designs, successfully identifying 7 new synthesis bugs. Additionally, by exploiting the optimization settings of EDA tools, we performed a compromised library mapping attack (CLiMA), creating a malicious version of hardware designs that remains undetectable by traditional verification methods. We also demonstrate how SynFuzz overcomes the limitations of the industry-standard formal verification tool, Cadence Conformal, providing a more robust and comprehensive approach to hardware verification.

cs.CR↗

arXiv2025

ReVise: A Human-AI Interface for Incremental Algorithmic Recourse

The recent adoption of artificial intelligence in socio-technical systems raises concerns about the black-box nature of the resulting decisions in fields such as hiring, finance, admissions, etc. If data subjects -- such as job applicants, loan applicants, and students -- receive an unfavorable outcome, they may be interested in algorithmic recourse, which involves updating certain features to yield a more favorable result when re-evaluated by algorithmic decision-making. Unfortunately, when individuals do not fully understand the incremental steps needed to change their circumstances, they risk following misguided paths that can lead to significant, long-term adverse consequences. Existing recourse approaches focus exclusively on the final recourse goal but neglect the possible incremental steps to reach the goal with real-life constraints, user preferences, and model artifacts. To address this gap, we formulate a visual analytic workflow for incremental recourse planning in collaboration with AI/ML experts and contribute an interactive visualization interface that helps data subjects efficiently navigate the recourse alternatives and make an informed decision. We present a usage scenario and subjective feedback from observational studies with twelve graduate students using a real-world dataset, which demonstrates that our approach can be instrumental for data subjects in choosing a suitable recourse path.

cs.HC↗

arXiv2025

LASA: Enhancing SoC Security Verification with LLM-Aided Property Generation

Ensuring the security of modern System-on-Chip (SoC) designs poses significant challenges due to increasing complexity and distributed assets across the intellectual property (IP) blocks. Formal property verification (FPV) provides the capability to model and validate design behaviors through security properties with model checkers; however, current practices require significant manual efforts to create such properties, making them time-consuming, costly, and error-prone. The emergence of Large Language Models (LLMs) has showcased remarkable proficiency across diverse domains, including HDL code generation and verification tasks. Current LLM-based techniques often produce vacuous assertions and lack efficient prompt generation, comprehensive verification, and bug detection. This paper presents LASA, a novel framework that leverages LLMs and retrieval-augmented generation (RAG) to produce non-vacuous security properties and SystemVerilog Assertions (SVA) from design specifications and related documentation for bus-based SoC designs. LASA integrates commercial EDA tool for FPV to generate coverage metrics and iteratively refines prompts through a feedback loop to enhance coverage. The effectiveness of LASA is validated through various open-source SoC designs, demonstrating high coverage values with an average of ~88\%, denoting comprehensive verification through efficient generation of security properties and SVAs. LASA also demonstrates bug detection capabilities, identifying five unique bugs in the buggy OpenTitan SoC from Hack@DAC'24 competition.

cs.CR↗

arXiv2025

Enhancing Test Efficiency through Automated ATPG-Aware Lightweight Scan Instrumentation

Scan-based Design-for-Testability (DFT) measures are prevalent in modern digital integrated circuits to achieve high test quality at low hardware cost. With the advent of 3D heterogeneous integration and chiplet-based systems, the role of scan is becoming ever more important due to its ability to make internal design nodes controllable and observable in a systematic and scalable manner. However, the effectiveness of scan-based DFT suffers from poor testability of internal nodes for complex circuits at deep logic levels. Existing solutions to address this problem primarily rely on Test Point Insertion (TPI) in the nodes with poor controllability or observability. However, TPI-based solutions, while an integral part of commercial practice, come at a high design and hardware cost. To address this issue, in this paper, we present LITE, a novel ATPG-aware lightweight scan instrumentation approach that utilizes the functional flip-flops in a scan chain to make multiple internal nodes observable and controllable in a low-cost, scalable manner. We provide both circuit-level design as well as an algorithmic approach for automating the insertion of LITE for design modifications. We show that LITE significantly improves the testability in terms of the number of patterns and test coverage for ATPG and random pattern testability, respectively, while incurring considerably lower overhead than TPI-based solutions.

cs.AR↗

arXiv2025

Library-Attack: Reverse Engineering Approach for Evaluating Hardware IP Protection

Existing countermeasures for hardware IP protection, such as obfuscation, camouflaging, and redaction, aim to defend against confidentiality and integrity attacks. However, within the current threat model, these techniques overlook the potential risks posed by a highly skilled adversary with privileged access to the IC supply chain, who may be familiar with critical IP blocks and the countermeasures implemented in the design. To address this scenario, we introduce Library-Attack, a novel reverse engineering technique that leverages privileged design information and prior knowledge of security countermeasures to recover sensitive hardware IP. During Library-Attack, a privileged attacker uses known design features to curate a design library of candidate IPs and employs structural comparison metrics from commercial EDA tools to identify the closest match. We evaluate Library-Attack on transformed ISCAS89 benchmarks to demonstrate potential vulnerabilities in existing IP-level countermeasures and propose an updated threat model to incorporate them.

cs.CR↗

arXiv2024

Fooling SHAP with Output Shuffling Attacks

Explainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-box models. If the method reveals a significant attribution from a ``protected feature'' (e.g., gender, race) on the model output, the model is considered unfair. However, adversarial attacks can subvert the detection of XAI methods. Previous approaches to constructing such an adversarial model require access to underlying data distribution, which may not be possible in many practical scenarios. We relax this constraint and propose a novel family of attacks, called shuffling attacks, that are data-agnostic. The proposed attack strategies can adapt any trained machine learning model to fool Shapley value-based explanations. We prove that Shapley values cannot detect shuffling attacks. However, algorithms that estimate Shapley values, such as linear SHAP and SHAP, can detect these attacks with varying degrees of effectiveness. We demonstrate the efficacy of the attack strategies by comparing the performance of linear SHAP and SHAP using real-world datasets.

cs.LG↗

arXiv2024

Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

Net load forecasting is crucial for energy planning and facilitating informed decision-making regarding trade and load distributions. However, evaluating forecasting models' performance against benchmark models remains challenging, thereby impeding experts' trust in the model's performance. In this context, there is a demand for technological interventions that allow scientists to compare models across various timeframes and solar penetration levels. This paper introduces a visual analytics-based application designed to compare the performance of deep-learning-based net load forecasting models with other models for probabilistic net load forecasting. This application employs carefully selected visual analytic interventions, enabling users to discern differences in model performance across different solar penetration levels, dataset resolutions, and hours of the day over multiple months. We also present observations made using our application through a case study, demonstrating the effectiveness of visualizations in aiding scientists in making informed decisions and enhancing trust in net load forecasting models.

cs.HC↗

arXiv2024

Interpretable Machine Learning for Weather and Climate Prediction: A Survey

Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede user trust and hinder further model improvements. As such, interpretable machine learning techniques have become crucial in enhancing the credibility and utility of weather and climate modeling. In this survey, we review current interpretable machine learning approaches applied to meteorological predictions. We categorize methods into two major paradigms: 1) Post-hoc interpretability techniques that explain pre-trained models, such as perturbation-based, game theory based, and gradient-based attribution methods. 2) Designing inherently interpretable models from scratch using architectures like tree ensembles and explainable neural networks. We summarize how each technique provides insights into the predictions, uncovering novel meteorological relationships captured by machine learning. Lastly, we discuss research challenges around achieving deeper mechanistic interpretations aligned with physical principles, developing standardized evaluation benchmarks, integrating interpretability into iterative model development workflows, and providing explainability for large foundation models.

physics.ao-ph↗

arXiv2023

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

Accurate net load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models.

cs.HC↗

arXiv2023

TRIVEA: Transparent Ranking Interpretation using Visual Explanation of Black-Box Algorithmic Rankers

Ranking schemes drive many real-world decisions, like, where to study, whom to hire, what to buy, etc. Many of these decisions often come with high consequences. For example, a university can be deemed less prestigious if not featured in a top-k list, and consumers might not even explore products that do not get recommended to buyers. At the heart of most of these decisions are opaque ranking schemes, which dictate the ordering of data entities, but their internal logic is inaccessible or proprietary. Drawing inferences about the ranking differences is like a guessing game to the stakeholders, like, the rankees (i.e., the entities who are ranked, like product companies) and the decision-makers (i.e., who use the rankings, like buyers). In this paper, we aim to enable transparency in ranking interpretation by using algorithmic rankers that learn from available data and by enabling human reasoning about the learned ranking differences using explainable AI (XAI) methods. To realize this aim, we leverage the exploration-explanation paradigm of human-data interaction to let human stakeholders explore subsets and groupings of complex multi-attribute ranking data using visual explanations of model fit and attribute influence on rankings. We realize this explanation paradigm for transparent ranking interpretation in TRIVEA, a visual analytic system that is fueled by: i) visualizations of model fit derived from algorithmic rankers that learn the associations between attributes and rankings from available data and ii) visual explanations derived from XAI methods that help abstract important patterns, like, the relative influence of attributes in different ranking ranges. Using TRIVEA, end users not trained in data science have the agency to transparently reason about the global and local behavior of the rankings without the need to open black-box ranking models and develop confidence in the resulting attribute-based inferences. We demonstrate the efficacy of TRIVEA using multiple usage scenarios and subjective feedback from researchers with diverse domain expertise. Keywords: Visual Analytics, Learning-to-Rank, Explainable ML, Ranking

cs.IR↗

arXiv2023

DIVAS: An LLM-based End-to-End Framework for SoC Security Analysis and Policy-based Protection

Securing critical assets in a bus-based System-On-Chip (SoC) is imperative to mitigate potential vulnerabilities and prevent unauthorized access, ensuring the integrity, availability, and confidentiality of the system. Ensuring security throughout the SoC design process is a formidable task owing to the inherent intricacies in SoC designs and the dispersion of assets across diverse IPs. Large Language Models (LLMs), exemplified by ChatGPT (OpenAI) and BARD (Google), have showcased remarkable proficiency across various domains, including security vulnerability detection and prevention in SoC designs. In this work, we propose DIVAS, a novel framework that leverages the knowledge base of LLMs to identify security vulnerabilities from user-defined SoC specifications, map them to the relevant Common Weakness Enumerations (CWEs), followed by the generation of equivalent assertions, and employ security measures through enforcement of security policies. The proposed framework is implemented using multiple ChatGPT and BARD models, and their performance was analyzed while generating relevant CWEs from the SoC specifications provided. The experimental results obtained from open-source SoC benchmarks demonstrate the efficacy of our proposed framework.

cs.CR↗

arXiv2023

Power to the Data Defenders: Human-Centered Disclosure Risk Calibration of Open Data

The open data ecosystem is susceptible to vulnerabilities due to disclosure risks. Though the datasets are anonymized during release, the prevalence of the release-and-forget model makes the data defenders blind to privacy issues arising after the dataset release. One such issue can be the disclosure risks in the presence of newly released datasets which may compromise the privacy of the data subjects of the anonymous open datasets. In this paper, we first examine some of these pitfalls through the examples we observed during a red teaming exercise and then envision other possible vulnerabilities in this context. We also discuss proactive risk monitoring, including developing a collection of highly susceptible open datasets and a visual analytic workflow that empowers data defenders towards undertaking dynamic risk calibration strategies.

cs.CR↗