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

As the scale and size of the data increases significantly nowadays, federal learning (Bonawitz et al. [2019]) for high performance computing and machine learning has been much more important than ever before (Abadi et al. [2016]). People…

Large Language Models (LLMs) are increasingly used for cybersecurity threat analysis, but their deployment in security-sensitive environments raises trust and safety concerns. With over 21,000 vulnerabilities disclosed in 2025, manual…

Discrepancies between scientific papers and their code undermine reproducibility, a concern that grows as automated research agents scale scientific output beyond human review capacity. Whether LLMs can reliably detect such discrepancies…

Active Learning (AL) aims to reduce the labeling burden by interactively selecting the most informative samples from a pool of unlabeled data. While there has been extensive research on improving AL query methods in recent years, some…

YARA has established itself as the de facto standard for "Detection as Code," enabling analysts and DevSecOps practitioners to define signatures for malware identification across the software supply chain. Despite its pervasive use, the…

The practice of fine-tuning Large Language Models (LLMs) has achieved state-of-the-art performance on specialized tasks, yet diagnosing why these models become brittle and fail to generalize remains a critical open problem. To address this,…

Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored.…

In-context learning (ICL) allows LLMs to adapt to new tasks via a few demonstrations, but those demonstrations may contain sensitive data. Differentially private (DP) ICL mechanisms mitigate this risk by injecting noise into the aggregation…

Introduction. Reservoir Computing is a bio-inspired computing paradigm for processing time-dependent signals. The performance of its hardware implementation is comparable to state-of-the-art digital algorithms on a series of benchmark…

The majority of quantum error detection and correction protocols assume that the population in a qubit does not leak outside of its computational subspace. For many existing approaches, however, the physical qubits do possess more than two…

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial…

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two…

Large Language Models (LLMs) are of great interest in vulnerability detection and repair. The effectiveness of these models hinges on the quality of the datasets used for both training and evaluation. Our investigation reveals that a number…

Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Predicting protein-ligand binding affinity is an essential part of computer-aided drug design. However, generalisable and performant global binding affinity models remain elusive, particularly in low data regimes. Despite the evolution of…

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity…