arXiv subjects

Martha Larson

Publications and source records attributed to Martha Larson.

At least 19 recordsLinked to original sources

arXiv2026

Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models

When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which it has been written or rendered. In this paper, we investigate whether, and how, the style in which a word is visualized in an image impacts the description that a Large Visual Language Model (LVLM) provides for the concept to which that word refers. Specifically, we investigate how functional text styles (readability-oriented, e.g., black sans-serif) versus decorative styles (display-oriented, e.g., colored cursive/script) affect LVLMs' descriptions of a concept in terms of the attributes of that concept. Our experiments study the situation in which the LVLM is able to correctly identify the concept referred to by a visual text, i.e., by a word or words rendered as an image, and in which the visual text style should not influence the attribute-based description that the LVLM produces. Our experimental results reveal that even when the concept is correctly identified, text style influences the model's attribute-based descriptions of the concept. Our findings demonstrate non-trivial style leakage from text style into semantic inference and motivate style-aware evaluation and mitigation for LVLM-based multimedia systems.

cs.CV↗

arXiv2026

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training

The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the importance of semantic data balance, adjusting the distribution of topics in the data to improve VLM accuracy. However, existing efficient pre-training approaches may disproportionately remove rare concepts from the training corpus. As a result, long-tail concepts remain insufficiently represented in the training data and are not effectively captured during training. In this work, we introduce a dynamic cluster-based sampling approach (DynamiCS) that downsamples large clusters of data and upsamples small ones. We first demonstrate the advantage of our cluster-scaling approach, which maintains the relative order of semantic clusters in the data and emphasizes the long-tail. This approach contrasts with current work, which focuses only on flattening the semantic distribution of the data. Then, we show the importance of dynamic sampling, which applies sampling at each epoch to improve cross-epoch data diversity and make upsampling practical. Our experiments show that DynamiCS reduces the computational cost of VLM training and provides a performance advantage for long-tail concepts. Code available at https://github.com/MingliangLiang3/DynamiCS.

cs.CV↗

arXiv2026

Voice Privacy from an Attribute-based Perspective

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.

cs.SD↗

arXiv2026

Talking to Extraordinary Objects: Folktales Offer Analogies for Interacting with Technology

Speech and language are valuable for interacting with technology. It would be ideal to be able to decouple their use from anthropomorphization, which has recently met an important moment of reckoning. In the world of folktales, language is everywhere and talking to extraordinary objects is not unusual. This overview presents examples of the analogies that folktales offer. Extraordinary objects in folktales are diverse and also memorable. Language capacity and intelligence are not always connected to humanness. Consideration of folktales can offer inspiration and insight for using speech and language for interacting with technology.

cs.CL↗

arXiv2025

RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification

Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representations. RECA-PD matches state-of-the-art performance in Speech-based PD detection while providing explanations that are more consistent and more clinically meaningful. Additionally, we demonstrate that performance degradation in certain speech tasks (e.g., monologue) can be mitigated by segmenting long recordings. Our findings indicate that performance and explainability are not necessarily mutually exclusive. Future work will enhance the usability of explanations for non-experts and explore severity estimation to increase the real-world clinical relevance.

cs.SD↗

arXiv2025

Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers

Speech-based Parkinson's disease (PD) detection has gained attention for its automated, cost-effective, and non-intrusive nature. As research studies usually rely on data from diagnostic-oriented speech tasks, this work explores the feasibility of diagnosing PD on the basis of speech data not originally intended for diagnostic purposes, using the Turn-Taking (TT) dataset. Our findings indicate that TT can be as useful as diagnostic-oriented PD datasets like PC-GITA. We also investigate which specific dataset characteristics impact PD classification performance. The results show that concatenating audio recordings and balancing participants' gender and status distributions can be beneficial. Cross-dataset evaluation reveals that models trained on PC-GITA generalize poorly to TT, whereas models trained on TT perform better on PC-GITA. Furthermore, we provide insights into the high variability across folds, which is mainly due to large differences in individual speaker performance.

eess.AS↗

arXiv2025

On Fact and Frequency: LLM Responses to Misinformation Expressed with Uncertainty

We study LLM judgments of misinformation expressed with uncertainty. Our experiments study the response of three widely used LLMs (GPT-4o, LlaMA3, DeepSeek-v2) to misinformation propositions that have been verified false and then are transformed into uncertain statements according to an uncertainty typology. Our results show that after transformation, LLMs change their factchecking classification from false to not-false in 25% of the cases. Analysis reveals that the change cannot be explained by predictors to which humans are expected to be sensitive, i.e., modality, linguistic cues, or argumentation strategy. The exception is doxastic transformations, which use linguistic cue phrases such as "It is believed ...".To gain further insight, we prompt the LLM to make another judgment about the transformed misinformation statements that is not related to truth value. Specifically, we study LLM estimates of the frequency with which people make the uncertain statement. We find a small but significant correlation between judgment of fact and estimation of frequency.

cs.CL↗

arXiv2025

Typographic Attacks in a Multi-Image Setting

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic attacks, broadening the current emphasis of the literature on attacking individual images. Specifically, our focus is on attacking image sets without repeating the attack query. Such non-repeating attacks are stealthier, as they are more likely to evade a gatekeeper than attacks that repeat the same attack text. We introduce two attack strategies for the multi-image setting, leveraging the difficulty of the target image, the strength of the attack text, and text-image similarity. Our text-image similarity approach improves attack success rates by 21% over random, non-specific methods on the CLIP model using ImageNet while maintaining stealth in a multi-image scenario. An additional experiment demonstrates transferability, i.e., text-image similarity calculated using CLIP transfers when attacking InstructBLIP.

cs.CR↗

arXiv2024

Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training

Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using a variety of strategies (truncation, random masking, block masking and syntax masking) and has reported syntax masking as the top performer. In this paper, we analyze the impact of different text masking strategies on the word frequency in the training data, and show that this impact is connected to model success. This finding motivates Contrastive Language-Image Pre-training with Word Frequency Masking (CLIPF), our proposed masking approach, which directly leverages word frequency. Extensive experiments demonstrate the advantages of CLIPF over syntax masking and other existing approaches, particularly when the number of input tokens decreases. We show that not only CLIPF, but also other existing masking strategies, outperform syntax masking when enough epochs are used during training, a finding of practical importance for selecting a text masking method for VLM training. Our code is available online.

cs.CV↗

arXiv2024

Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency

We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method that improves the efficiency of VLMs. Unlike MetaCLIP, our method does not need metadata for pruning, but selects text-image pairs to prune based on the content of the text. Specifically, WFPP prunes text-image pairs containing high-frequency words across the entire training dataset. The effect of WFPP is to reduce the dominance of frequent words. The result a better balanced word-frequency distribution in the dataset, which is known to improve the training of word embedding models. After pre-training on the pruned subset, we fine-tuned the model on the entire dataset for one additional epoch to achieve better performance. Our experiments demonstrate that applying WFPP when training a CLIP model improves performance on a wide range of downstream tasks. WFPP also provides the advantage of speeding up pre-training by using fewer samples. Additionally, we analyze the training data before and after pruning to visualize how WFPP changes the balance of word frequencies. We hope our work encourages researchers to consider the distribution of words in the training data when pre-training VLMs, not limited to CLIP.

cs.LG↗

arXiv2024

Scenario of Use Scheme: Threat Model Specification for Speaker Privacy Protection in the Medical Domain

Speech recordings are being more frequently used to detect and monitor disease, leading to privacy concerns. Beyond cryptography, protection of speech can be addressed by approaches, such as perturbation, disentanglement, and re-synthesis, that eliminate sensitive information of the speaker, leaving the information necessary for medical analysis purposes. In order for such privacy protective approaches to be developed, clear and systematic specifications of assumptions concerning medical settings and the needs of medical professionals are necessary. In this paper, we propose a Scenario of Use Scheme that incorporates an Attacker Model, which characterizes the adversary against whom the speaker's privacy must be defended, and a Protector Model, which specifies the defense. We discuss the connection of the scheme with previous work on speech privacy. Finally, we present a concrete example of a specified Scenario of Use and a set of experiments about protecting speaker data against gender inference attacks while maintaining utility for Parkinson's detection.

eess.AS↗

arXiv2024

Centered Masking for Language-Image Pre-Training

We introduce Gaussian masking for Language-Image Pre-Training (GLIP) a novel, straightforward, and effective technique for masking image patches during pre-training of a vision-language model. GLIP builds on Fast Language-Image Pre-Training (FLIP), which randomly masks image patches while training a CLIP model. GLIP replaces random masking with centered masking, that uses a Gaussian distribution and is inspired by the importance of image patches at the center of the image. GLIP retains the same computational savings as FLIP, while improving performance across a range of downstream datasets and tasks, as demonstrated by our experimental results. We show the benefits of GLIP to be easy to obtain, requiring no delicate tuning of the Gaussian, and also applicable to data sets containing images without an obvious center focus.

cs.CV↗

arXiv2023

Backdoor Attacks on Transformers for Tabular Data: An Empirical Study

Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern. These attacks involve the subtle insertion of triggers during model training, allowing for manipulated predictions. More recently, DNNs used with tabular data have gained increasing attention due to the rise of transformer models. Our research presents a comprehensive analysis of backdoor attacks on tabular data using DNNs, mainly focusing on transformers. We propose a novel approach for trigger construction: in-bounds attack, which provides excellent attack performance while maintaining stealthiness. Through systematic experimentation across benchmark datasets, we uncover that transformer-based DNNs for tabular data are highly susceptible to backdoor attacks, even with minimal feature value alterations. We also verify that these attacks can be generalized to other models, like XGBoost and DeepFM. Our results demonstrate up to 100% attack success rate with negligible clean accuracy drop. Furthermore, we evaluate several defenses against these attacks, identifying Spectral Signatures as the most effective. Still, our findings highlight the need to develop tabular data-specific countermeasures to defend against backdoor attacks.

cs.CR↗

arXiv2023

When Machine Learning Models Leak: An Exploration of Synthetic Training Data

We investigate an attack on a machine learning model that predicts whether a person or household will relocate in the next two years, i.e., a propensity-to-move classifier. The attack assumes that the attacker can query the model to obtain predictions and that the marginal distribution of the data on which the model was trained is publicly available. The attack also assumes that the attacker has obtained the values of non-sensitive attributes for a certain number of target individuals. The objective of the attack is to infer the values of sensitive attributes for these target individuals. We explore how replacing the original data with synthetic data when training the model impacts how successfully the attacker can infer sensitive attributes.

cs.LG↗

arXiv2023

Beyond Neural-on-Neural Approaches to Speaker Gender Protection

Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive attribute. Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i.e., perturbations are generated and tested with a neural network. In this paper, we propose to go beyond this practice to strengthen the study of gender protection. First, we demonstrate the importance of testing gender inference attacks that are based on speech features historically developed by speech scientists, alongside the conventionally used neural classifiers. Next, we argue that researchers should use speech features to gain insight into how protective modifications change the speech signal. Finally, we point out that gender-protection algorithms should be compared with novel "vocal adversaries", human-executed voice adaptations, in order to improve interpretability and enable before-the-mic protection.

eess.AS↗

arXiv2023

Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression

Perturbative availability poisons (PAPs) add small changes to images to prevent their use for model training. Current research adopts the belief that practical and effective approaches to countering PAPs do not exist. In this paper, we argue that it is time to abandon this belief. We present extensive experiments showing that 12 state-of-the-art PAP methods are vulnerable to Image Shortcut Squeezing (ISS), which is based on simple compression. For example, on average, ISS restores the CIFAR-10 model accuracy to $81.73\%$, surpassing the previous best preprocessing-based countermeasures by $37.97\%$ absolute. ISS also (slightly) outperforms adversarial training and has higher generalizability to unseen perturbation norms and also higher efficiency. Our investigation reveals that the property of PAP perturbations depends on the type of surrogate model used for poison generation, and it explains why a specific ISS compression yields the best performance for a specific type of PAP perturbation. We further test stronger, adaptive poisoning, and show it falls short of being an ideal defense against ISS. Overall, our results demonstrate the importance of considering various (simple) countermeasures to ensure the meaningfulness of analysis carried out during the development of PAP methods.

cs.CR↗

arXiv2022

Generative Poisoning Using Random Discriminators

We introduce ShortcutGen, a new data poisoning attack that generates sample-dependent, error-minimizing perturbations by learning a generator. The key novelty of ShortcutGen is the use of a randomly-initialized discriminator, which provides spurious shortcuts needed for generating poisons. Different from recent, iterative methods, our ShortcutGen can generate perturbations with only one forward pass in a label-free manner, and compared to the only existing generative method, DeepConfuse, our ShortcutGen is faster and simpler to train while remaining competitive. We also demonstrate that integrating a simple augmentation strategy can further boost the robustness of ShortcutGen against early stopping, and combining augmentation and non-augmentation leads to new state-of-the-art results in terms of final validation accuracy, especially in the challenging, transfer scenario. Lastly, we speculate, through uncovering its working mechanism, that learning a more general representation space could allow ShortcutGen to work for unseen data.

cs.LG↗

arXiv2022

Minimizing Mindless Mentions: Recommendation with Minimal Necessary User Reviews

Recently, researchers have turned their attention to recommender systems that use only minimal necessary data. This trend is informed by the idea that recommender systems should use no more user interactions than are needed in order to provide users with useful recommendations. In this position paper, we make the case for applying the idea of minimal necessary data to recommender systems that use user reviews. We argue that the content of individual user reviews should be subject to minimization. Specifically, reviews used as training data to generate recommendations or reviews used to help users decide on purchases or consumption should be automatically edited to contain only the information that is needed.

cs.IR↗