Related papers: A Critique of ANSI SQL Isolation Levels
Information-flow security type systems ensure confidentiality by enforcing noninterference: a program cannot leak private data to public channels. However, in practice, programs need to selectively declassify information about private data.…
Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently protected against broader memorization risks. However, we…
Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and…
Standard datasets are frequently used to train and evaluate Machine Learning models. However, the assumed standardness of these datasets leads to a lack of in-depth discussion on how their labels match the derived categories for the…
Existing entailment datasets mainly pose problems which can be answered without attention to grammar or word order. Learning syntax requires comparing examples where different grammar and word order change the desired classification. We…
The isolation level Multiversion Read Committed (RC), offered by many database systems, is known to trade consistency for increased transaction throughput. Sometimes, transaction workloads can be safely executed under RC obtaining the…
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…
Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…
Distant supervision makes it possible to automatically label bags of sentences for relation extraction by leveraging knowledge bases, but suffers from the sparse and noisy bag issues. Additional information sources are urgently needed to…
Detecting and classifying abnormal system states is critical for condition monitoring, but supervised methods often fall short due to the rarity of anomalies and the lack of labeled data. Therefore, clustering is often used to group similar…
Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…
We study example-level private supervised speech classification under a practical release constraint: training may access privileged side information, but the released model must be audio-only. This setting is important because speech…
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…
A new emerging paradigm of Uncertain Risk of Suspicion, Threat and Danger, observed across the field of information security, is described. Based on this paradigm a novel approach to anomaly detection is presented. Our approach is based on…
Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel…
Subjective NLP datasets typically aggregate annotator judgments into a single gold label, making it difficult to diagnose whether disagreement reflects unclear criteria, collapsed distinctions, or legitimate plurality. We propose a…
From buying books to finding the perfect partner, we share our most intimate wants and needs with our favourite online systems. But how far should we accept promises of privacy in the face of personal profiling? In particular we ask how can…
Sequential pattern discovery is a well-studied field in data mining. Episodes are sequential patterns describing events that often occur in the vicinity of each other. Episodes can impose restrictions to the order of the events, which makes…
This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…
Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have…