Search

Open domain question answering systems frequently rely on information retrieved from large collections of text (such as the Web) to answer questions. However, such collections of text often contain conflicting information, and indiscriminately depending on this information may result in untruthful and inaccurate answers. To understand the gravity of this problem, we collect a human-annotated dataset, Question Answering with Conflicting Contexts (QACC), and find that as much as 25% of unambiguous, open domain questions can lead to conflicting contexts when retrieved using Google Search. We evaluate and benchmark three powerful Large Language Models (LLMs) with our dataset QACC and demonstrate their limitations in effectively addressing questions with conflicting information. To explore how humans reason through conflicting contexts, we request our annotators to provide explanations for their selections of correct answers. We demonstrate that by finetuning LLMs to explain their answers, we can introduce richer information into their training that guide them through the process of reasoning with conflicting contexts.

Affordance, defined as the potential actions that an object offers, is crucial for robotic manipulation tasks. A deep understanding of affordance can lead to more intelligent AI systems. For example, such knowledge directs an agent to grasp a knife by the handle for cutting and by the blade when passing it to someone. In this paper, we present a streamlined affordance learning system that encompasses data collection, effective model training, and robot deployment. First, we collect training data from egocentric videos in an automatic manner. Different from previous methods that focus only on the object graspable affordance and represent it as coarse heatmaps, we cover both graspable (e.g., object handles) and functional affordances (e.g., knife blades, hammer heads) and extract data with precise segmentation masks. We then propose an effective model, termed Geometry-guided Affordance Transformer (GKT), to train on the collected data. GKT integrates an innovative Depth Feature Injector (DFI) to incorporate 3D shape and geometric priors, enhancing the model's understanding of affordances. To enable affordance-oriented manipulation, we further introduce Aff-Grasp, a framework that combines GKT with a grasp generation model. For comprehensive evaluation, we create an affordance evaluation dataset with pixel-wise annotations, and design real-world tasks for robot experiments. The results show that GKT surpasses the state-of-the-art by 15.9% in mIoU, and Aff-Grasp achieves high success rates of 95.5% in affordance prediction and 77.1% in successful grasping among 179 trials, including evaluations with seen, unseen objects, and cluttered scenes., Comment: Project page: https://reagan1311.github.io/affgrasp

Securing endpoints is challenging due to the evolving nature of threats and attacks. With endpoint logging systems becoming mature, provenance-graph representations enable the creation of sophisticated behavior rules. However, adapting to the pace of emerging attacks is not scalable with rules. This led to the development of ML models capable of learning from endpoint logs. However, there are still open challenges: i) malicious patterns of malware are spread across long sequences of events, and ii) ML classification results are not interpretable. To address these issues, we develop and present EagleEye, a novel system that i) uses rich features from provenance graphs for behavior event representation, including command-line embeddings, ii) extracts long sequences of events and learns event embeddings, and iii) trains a lightweight Transformer model to classify behavior sequences as malicious or not. We evaluate and compare EagleEye against state-of-the-art baselines on two datasets, namely a new real-world dataset from a corporate environment, and the public DARPA dataset. On the DARPA dataset, at a false-positive rate of 1%, EagleEye detects $\approx$89% of all malicious behavior, outperforming two state-of-the-art solutions by an absolute margin of 38.5%. Furthermore, we show that the Transformer's attention mechanism can be leveraged to highlight the most suspicious events in a long sequence, thereby providing interpretation of malware alerts., Comment: Accepted as research paper at eCrime 2024; update affiliations

To address the challenging problem of detecting phishing webpages, researchers have developed numerous solutions, in particular those based on machine learning (ML) algorithms. Among these, brand-based phishing detection that uses models from Computer Vision to detect if a given webpage is imitating a well-known brand has received widespread attention. However, such models are costly and difficult to maintain, as they need to be retrained with labeled dataset that has to be regularly and continuously collected. Besides, they also need to maintain a good reference list of well-known websites and related meta-data for effective performance. In this work, we take steps to study the efficacy of large language models (LLMs), in particular the multimodal LLMs, in detecting phishing webpages. Given that the LLMs are pretrained on a large corpus of data, we aim to make use of their understanding of different aspects of a webpage (logo, theme, favicon, etc.) to identify the brand of a given webpage and compare the identified brand with the domain name in the URL to detect a phishing attack. We propose a two-phase system employing LLMs in both phases: the first phase focuses on brand identification, while the second verifies the domain. We carry out comprehensive evaluations on a newly collected dataset. Our experiments show that the LLM-based system achieves a high detection rate at high precision; importantly, it also provides interpretable evidence for the decisions. Our system also performs significantly better than a state-of-the-art brand-based phishing detection system while demonstrating robustness against two known adversarial attacks., Comment: To appear in eCrime 2024

Phishing attacks attempt to deceive users into stealing sensitive information, posing a significant cybersecurity threat. Advances in machine learning (ML) and deep learning (DL) have led to the development of numerous phishing webpage detection solutions, but these models remain vulnerable to adversarial attacks. Evaluating their robustness against adversarial phishing webpages is essential. Existing tools contain datasets of pre-designed phishing webpages for a limited number of brands, and lack diversity in phishing features. To address these challenges, we develop PhishOracle, a tool that generates adversarial phishing webpages by embedding diverse phishing features into legitimate webpages. We evaluate the robustness of two existing models, Stack model and Phishpedia, in classifying PhishOracle-generated adversarial phishing webpages. Additionally, we study a commercial large language model, Gemini Pro Vision, in the context of adversarial attacks. We conduct a user study to determine whether PhishOracle-generated adversarial phishing webpages deceive users. Our findings reveal that many PhishOracle-generated phishing webpages evade current phishing webpage detection models and deceive users, but Gemini Pro Vision is robust to the attack. We also develop the PhishOracle web app, allowing users to input a legitimate URL, select relevant phishing features and generate a corresponding phishing webpage. All resources are publicly available on GitHub.

Completing complex tasks in unpredictable settings like home kitchens challenges robotic systems. These challenges include interpreting high-level human commands, such as "make me a hot beverage" and performing actions like pouring a precise amount of water into a moving mug. To address these challenges, we present a novel framework that combines Large Language Models (LLMs), a curated Knowledge Base, and Integrated Force and Visual Feedback (IFVF). Our approach interprets abstract instructions, performs long-horizon tasks, and handles various uncertainties. It utilises GPT-4 to analyse the user's query and surroundings, then generates code that accesses a curated database of functions during execution. It translates abstract instructions into actionable steps. Each step involves generating custom code by employing retrieval-augmented generalisation to pull IFVF-relevant examples from the Knowledge Base. IFVF allows the robot to respond to noise and disturbances during execution. We use coffee making and plate decoration to demonstrate our approach, including components ranging from pouring to drawer opening, each benefiting from distinct feedback types and methods. This novel advancement marks significant progress toward a scalable, efficient robotic framework for completing complex tasks in uncertain environments. Our findings are illustrated in an accompanying video and supported by an open-source GitHub repository (released upon paper acceptance).

Cambodia's agricultural landscape is rapidly transforming, particularly in the cashew sector. Despite the country's rapid emergence and ambition to become the largest cashew producer, comprehensive data on plantation areas and the environmental impacts of this expansion are lacking. This study addresses the gap in detailed land use data for cashew plantations in Cambodia and assesses the implications of agricultural advancements. We collected over 80,000 training polygons across Cambodia to train a convolutional neural network using high-resolution optical and SAR satellite data for precise cashew plantation mapping. Our findings indicate that Cambodia ranks among the top five in terms of cultivated area and the top three in global cashew production, driven by high yields. Significant cultivated areas are located in Kampong Thom, Kratie, and Ratanak Kiri provinces. Balancing rapid agricultural expansion with environmental stewardship, particularly forest conservation, is crucial. Cambodia's cashew production is poised for further growth, driven by high-yielding trees and premium nuts. However, sustainable expansion requires integrating agricultural practices with economic and environmental strategies to enhance local value and protect forested areas. Advanced mapping technologies offer comprehensive tools to support these objectives and ensure the sustainable development of Cambodia's cashew industry., Comment: 13 pages, 5 figures, 4 tables

Large language models (LLMs) are a class of powerful and versatile models that are beneficial to many industries. With the emergence of LLMs, we take a fresh look at cyber security, specifically exploring and summarizing the potential of LLMs in addressing challenging problems in the security and safety domains.

Quantification, also known as class prevalence estimation, is the supervised learning task in which a model is trained to predict the prevalence of each class in a given bag of examples. This paper investigates the application of deep neural networks to tasks of quantification in scenarios where it is possible to apply a symmetric supervised approach that eliminates the need for classification as an intermediary step, directly addressing the quantification problem. Additionally, it discusses existing permutation-invariant layers designed for set processing and assesses their suitability for quantification. In light of our analysis, we propose HistNetQ, a novel neural architecture that relies on a permutation-invariant representation based on histograms that is specially suited for quantification problems. Our experiments carried out in the only quantification competition held to date, show that HistNetQ outperforms other deep neural architectures devised for set processing, as well as the state-of-the-art quantification methods. Furthermore, HistNetQ offers two significant advantages over traditional quantification methods: i) it does not require the labels of the training examples but only the prevalence values of a collection of training bags, making it applicable to new scenarios; and ii) it is able to optimize any custom quantification-oriented loss function.

DNS, one of the fundamental protocols of the TCP/IP stack, has evolved over the years to protect against threats and attacks. This study examines the risks associated with DNS and explores recent advancements that contribute towards making the DNS ecosystem resilient against various attacks while safeguarding user privacy., Comment: 9 pages, 4 figures - original manuscript submitted to IEEE Security & Privacy Magazine

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. In this study, we used globally representative data from the ENIGMA-MDD working group containing an extensive sample of people with MDD (N=2,772) and HC (N=4,240), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. As we analyzed a multi-site sample, we additionally applied the ComBat harmonization tool to remove potential nuisance effects of site. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of features and classifiers is unfeasible.

Recent research works have proposed machine learning models for classifying IoT devices connected to a network. However, there is still a practical challenge of not having all devices (and hence their traffic) available during the training of a model. This essentially means, during the operational phase, we need to classify new devices not seen in the training phase. To address this challenge, we propose ZEST -- a ZSL (zero-shot learning) framework based on self-attention for classifying both seen and unseen devices. ZEST consists of i) a self-attention based network feature extractor, termed SANE, for extracting latent space representations of IoT traffic, ii) a generative model that trains a decoder using latent features to generate pseudo data, and iii) a supervised model that is trained on the generated pseudo data for classifying devices. We carry out extensive experiments on real IoT traffic data; our experiments demonstrate i) ZEST achieves significant improvement (in terms of accuracy) over the baselines; ii) SANE is able to better extract meaningful representations than LSTM which has been commonly used for modeling network traffic., Comment: 9 pages, 6 figures, 3 tables