Related papers: Inoculation by Fine-Tuning: A Method for Analyzing…

Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI),…

While machine learning is currently transforming the field of histopathology, the domain lacks a comprehensive evaluation of state-of-the-art models based on essential but complementary quality requirements beyond a mere classification…

Backdoor and data-poisoning attacks can flip predictions with tiny training corruptions, yet a sharp theory linking poisoning strength, overparameterization, and regularization is lacking. We analyze ridge least squares with an unpenalized…

Densely annotated medical image datasets that capture not only diagnostic labels but also the underlying reasoning behind these diagnoses are scarce. Such reasoning-related annotations are essential for developing and evaluating explainable…

We present a novel methodology for integrating high resolution longitudinal data with the dynamic prediction capabilities of survival models. The aim is two-fold: to improve the predictive power while maintaining interpretability of the…

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Histopathology can help clinicians make accurate diagnoses, determine disease prognosis, and plan appropriate treatment strategies. As deep learning techniques prove successful in the medical domain, the primary challenges become limited…

A fundamental approach in neuroscience research is to test hypotheses based on neuropsychological and behavioral measures, i.e., whether certain factors (e.g., related to life events) are associated with an outcome (e.g., depression). In…

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such as medical image analysis, this phenomenon may prevent…

While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…

Foundation models in digital pathology use massive datasets to learn useful compact feature representations of complex histology images. However, there is limited transparency into what drives the correlation between dataset size and…

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

Deep neural networks (DNNs) have rapidly become a \textit{de facto} choice for medical image understanding tasks. However, DNNs are notoriously fragile to the class imbalance in image classification. We further point out that such imbalance…

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

With the steady rise of the use of AI in bio-technical applications and the widespread adoption of genomics sequencing, an increasing amount of AI-based algorithms and tools is entering the research and production stage affecting critical…

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…