Related papers: Data Leakage and Redundancy in the LIT-PCBA Benchm…

Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…

We introduce When Alpha Disappears, a paired evaluation benchmark for diagnosing decision-time leakage in financial machine-learning backtests. Rather than treating leakage as a binary property, the benchmark estimates protocol-induced…

To enhance documentation and maintenance practices, developers conventionally establish links between related software artifacts manually. Empirical research has revealed that developers frequently overlook this practice, resulting in…

Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become…

Machine learning (ML) models benefit from large datasets. Collecting data in biomedical domains is costly and challenging, hence, combining datasets has become a common practice. However, datasets obtained under different conditions could…

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…

Leakage errors are unwanted transfer of population outside of a defined computational subspace and they occur in almost every platform for quantum computing. While prevalent, leakage is often overlooked when measuring and reporting the…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

We introduce LinAlg-Bench, a diagnostic benchmark evaluating 10 frontier large language models on structured linear algebra computation across a strict dimensional gradient of 3x3, 4x4, and 5x5 matrices. Spanning 9 task types and 660…

Neural retrieval models are often trained on (subsets of) the millions of queries of the MS MARCO / ORCAS datasets and then tested on the 250 Robust04 queries or other TREC benchmarks with often only 50 queries. In such setups, many of the…

Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. However, their reliance on extensive and often undisclosed pre-training datasets raises significant…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing success of these…

Errors are common issues in quantum computing platforms, among which leakage is one of the most challenging to address. This is because leakage, i.e., the loss of information stored in the computational subspace to undesired subspaces in a…

Advanced Persistent Threats (APTs) pose a severe challenge to cyber defense due to their stealthy behavior and the extreme class imbalance inherent in detection datasets. To address these issues, we propose a novel active learning-based…

Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model. This phenomenon renders a model excessively optimistic or even useless in the real…

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-Bench, provide standardized and transparent evaluation protocols that support comparative analysis, reproducibility, and systematic progress tracking in Language Model (LM)…

Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from above $95\%$ to under $5\%$. Empirical defenses…

While prior work has shown that Federated Learning updates can leak sensitive information, label reconstruction attacks, which aim to recover input labels from shared gradients, have not yet been examined in the context of Human Activity…

The use of learning-based techniques to achieve automated software vulnerability detection has been of longstanding interest within the software security domain. These data-driven solutions are enabled by large software vulnerability…