相关论文: How Train-Test Leakage Affects Zero-shot Retrieval

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…

This is the third year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels available for both passage and document ranking tasks. In…

Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…

Code review is a key practice in software engineering, ensuring quality and collaboration. However, industrial Merge Request (MR) workflows often deviate from standardized review processes, with many MRs serving non-review purposes (e.g.,…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memorization are generally unclear, particularly in scenarios where…

Various studies among side-channel attacks have tried to extract information through leakages from electronic devices to reach the instruction flow of some appliances. However, previous methods highly depend on the resolution of traced…

Large language models confidently produce outdated answers, and no existing method can detect them. We show this is not an engineering failure but a structural one: temporal drift, whether a stored fact has changed since training, is…

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…

This study examines the impact of data snooping on neural networks used to detect vulnerabilities in lifted code, and builds on previous research that used word2vec and unidirectional and bidirectional transformer-based embeddings. The…

Given the ease of creating synthetic data from machine learning models, new models can be potentially trained on synthetic data generated by previous models. This recursive training process raises concerns about the long-term impact on…

When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels…

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear…

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…

Machine learning algorithms, especially Neural Networks (NNs), are a valuable tool used to approximate non-linear relationships, like the AC-Optimal Power Flow (AC-OPF), with considerable accuracy -- and achieving a speedup of several…

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…

Ideally Open-Domain Question Answering models should exhibit a number of competencies, ranging from simply memorizing questions seen at training time, to answering novel question formulations with answers seen during training, to…