While large language models excel in a variety of natural language processing (NLP) tasks, to perform well on spoken language understanding (SLU) tasks, they must either rely on off-the-shelf automatic speech recognition (ASR) systems for transcription, or be equipped with an in-built speech modality. This work focuses on the former scenario, where LLM's accuracy on SLU tasks is constrained by the accuracy of a fixed ASR system on the spoken input. Specifically, we tackle speech-intent classification task, where a high word-error-rate can limit the LLM's ability to understand the spoken intent. Instead of chasing a high accuracy by designing complex or specialized architectures regardless of deployment costs, we seek to answer how far we can go without substantially changing the underlying ASR and LLM, which can potentially be shared by multiple unrelated tasks. To this end, we propose prompting the LLM with an n-best list of ASR hypotheses instead of only the error-prone 1-best hypothesis. We explore prompt-engineering to explain the concept of n-best lists to the LLM; followed by the finetuning of Low-Rank Adapters on the downstream tasks. Our approach using n-best lists proves to be effective on a device-directed speech detection task as well as on a keyword spotting task, where systems using n-best list prompts outperform those using 1-best ASR hypothesis; thus paving the way for an efficient method to exploit ASR uncertainty via LLMs for speech-based applications.

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We collect and analyze 229 research papers from 2017 to 2023 to answer four key research questions (RQs). In RQ1, we categorize different LLMs that have been employed in SE tasks, characterizing their distinctive features and uses. In RQ2, we analyze the methods used in data collection, preprocessing, and application highlighting the role of well-curated datasets for successful LLM for SE implementation. RQ3 investigates the strategies employed to optimize and evaluate the performance of LLMs in SE. Finally, RQ4 examines the specific SE tasks where LLMs have shown success to date, illustrating their practical contributions to the field. From the answers to these RQs, we discuss the current state-of-the-art and trends, identifying gaps in existing research, and flagging promising areas for future study.

The emergence of a variety of Machine Learning (ML) approaches for travel mode choice prediction poses an interesting question to transport modellers: which models should be used for which applications? The answer to this question goes beyond simple predictive performance, and is instead a balance of many factors, including behavioural interpretability and explainability, computational complexity, and data efficiency. There is a growing body of research which attempts to compare the predictive performance of different ML classifiers with classical random utility models. However, existing studies typically analyse only the disaggregate predictive performance, ignoring other aspects affecting model choice. Furthermore, many studies are affected by technical limitations, such as the use of inappropriate validation schemes, incorrect sampling for hierarchical data, lack of external validation, and the exclusive use of discrete metrics. We address these limitations by conducting a systematic comparison of different modelling approaches, across multiple modelling problems, in terms of the key factors likely to affect model choice (out-of-sample predictive performance, accuracy of predicted market shares, extraction of behavioural indicators, and computational efficiency). We combine several real world datasets with synthetic datasets, where the data generation function is known. The results indicate that the models with the highest disaggregate predictive performance (namely extreme gradient boosting and random forests) provide poorer estimates of behavioural indicators and aggregate mode shares, and are more expensive to estimate, than other models, including deep neural networks and Multinomial Logit (MNL). It is further observed that the MNL model performs robustly in a variety of situations, though ML techniques can improve the estimates of behavioural indices such as Willingness to Pay.

Matching algorithms are commonly used to predict matches between items in a collection. For example, in 1:1 face verification, a matching algorithm predicts whether two face images depict the same person. Accurately assessing the uncertainty of the error rates of such algorithms can be challenging when data are dependent and error rates are low, two aspects that have been often overlooked in the literature. In this work, we review methods for constructing confidence intervals for error rates in 1:1 matching tasks. We derive and examine the statistical properties of these methods, demonstrating how coverage and interval width vary with sample size, error rates, and degree of data dependence on both analysis and experiments with synthetic and real-world datasets. Based on our findings, we provide recommendations for best practices for constructing confidence intervals for error rates in 1:1 matching tasks.

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging from autopilot disengagements due to inactive traffic lights carried by trucks to phantom braking caused by images of stop signs on roadside billboards. These system-level failures are not due to failures of any individual component of the autonomy stack but rather system-level deficiencies in semantic reasoning. Such edge cases, which we call semantic anomalies, are simple for a human to disentangle yet require insightful reasoning. To this end, we study the application of large language models (LLMs), endowed with broad contextual understanding and reasoning capabilities, to recognize such edge cases and introduce a monitoring framework for semantic anomaly detection in vision-based policies. Our experiments apply this framework to a finite state machine policy for autonomous driving and a learned policy for object manipulation. These experiments demonstrate that the LLM-based monitor can effectively identify semantic anomalies in a manner that shows agreement with human reasoning. Finally, we provide an extended discussion on the strengths and weaknesses of this approach and motivate a research outlook on how we can further use foundation models for semantic anomaly detection.

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum, when in reality, ML models are part of larger systems that include components for training data filtering, output monitoring, and more. In this work, we introduce privacy side channels: attacks that exploit these system-level components to extract private information at far higher rates than is otherwise possible for standalone models. We propose four categories of side channels that span the entire ML lifecycle (training data filtering, input preprocessing, output post-processing, and query filtering) and allow for either enhanced membership inference attacks or even novel threats such as extracting users' test queries. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. Moreover, we show that systems which block language models from regenerating training data can be exploited to allow exact reconstruction of private keys contained in the training set -- even if the model did not memorize these keys. Taken together, our results demonstrate the need for a holistic, end-to-end privacy analysis of machine learning.

The last decades have seen a growth in the number of cyber-attacks with severe economic and privacy damages, which reveals the need for network intrusion detection approaches to assist in preventing cyber-attacks and reducing their risks. In this work, we propose a novel network representation as a graph of flows that aims to provide relevant topological information for the intrusion detection task, such as malicious behavior patterns, the relation between phases of multi-step attacks, and the relation between spoofed and pre-spoofed attackers activities. In addition, we present a Graph Neural Network (GNN) based framework responsible for exploiting the proposed graph structure to classify communication flows by assigning them a maliciousness score. The framework comprises three main steps that aim to embed nodes features and learn relevant attack patterns from the network representation. Finally, we highlight a potential data leakage issue with classical evaluation procedures and suggest a solution to ensure a reliable validation of intrusion detection systems performance. We implement the proposed framework and prove that exploiting the flow-based graph structure outperforms the classical machine learning-based and the previous GNN-based solutions.

The evaluation data was randomly sampled using K-fold Cross Validation. The model trained was able to reliably identify lifting and non-lifting events from data gathered under the same conditions as its training I.

The notion of individual fairness is a formalization of an ethical principle, "Treating like cases alike," which has been argued such as by Aristotle. In a fairness-aware machine learning context, Dwork et al. firstly formalized the notion. In their formalization, a similar pair of data in an unfair space should be mapped to similar positions in a fair space. We propose to re-formalize individual fairness by the statistical independence conditioned by individuals. This re-formalization has the following merits. First, our formalization is compatible with that of Dwork et al. Second, our formalization enables to combine individual fairness with the fairness notion, equalized odds or sufficiency, as well as statistical parity. Third, though their formalization implicitly assumes a pre-process approach for making fair prediction, our formalization is applicable to an in-process or post-process approach.

Peer review is the method employed by the scientific community for evaluating research advancements. In the field of cybersecurity, the practice of double-blind peer review is the de-facto standard. This paper touches on the holy grail of peer reviewing and aims to shed light on the performance of AI in reviewing for academic security conferences. Specifically, we investigate the predictability of reviewing outcomes by comparing the results obtained from human reviewers and machine-learning models. To facilitate our study, we construct a comprehensive dataset by collecting thousands of papers from renowned computer science conferences and the arXiv preprint website. Based on the collected data, we evaluate the prediction capabilities of ChatGPT and a two-stage classification approach based on the Doc2Vec model with various classifiers. Our experimental evaluation of review outcome prediction using the Doc2Vec-based approach performs significantly better than the ChatGPT and achieves an accuracy of over 90%. While analyzing the experimental results, we identify the potential advantages and limitations of the tested ML models. We explore areas within the paper-reviewing process that can benefit from automated support approaches, while also recognizing the irreplaceable role of human intellect in certain aspects that cannot be matched by state-of-the-art AI techniques.