APT, known as Advanced Persistent Threat, is a difficult challenge for cyber defence. These threats make many traditional defences ineffective as the vulnerabilities exploited by these threats are insiders who have access to and are within the network. This paper proposes DeepTaskAPT, a heterogeneous task-tree based deep learning method to construct a baseline model based on sequences of tasks using a Long Short-Term Memory (LSTM) neural network that can be applied across different users to identify anomalous behaviour. Rather than applying the model to sequential log entries directly, as most current approaches do, DeepTaskAPT applies a process tree based task generation method to generate sequential log entries for the deep learning model. To assess the performance of DeepTaskAPT, we use a recently released synthetic dataset, DARPA Operationally Transparent Computing (OpTC) dataset and a real-world dataset, Los Alamos National Laboratory (LANL) dataset. Both of them are composed of host-based data collected from sensors. Our results show that DeepTaskAPT outperforms similar approaches e.g. DeepLog and the DeepTaskAPT baseline model demonstrate its capability to detect malicious traces in various attack scenarios while having high accuracy and low false-positive rates. To the best of knowledge this is the very first attempt of using recently introduced OpTC dataset for cyber threat detection.

We investigate whether model extraction can be used to "steal" the weights of sequential recommender systems, and the potential threats posed to victims of such attacks. This type of risk has attracted attention in image and text classification, but to our knowledge not in recommender systems. We argue that sequential recommender systems are subject to unique vulnerabilities due to the specific autoregressive regimes used to train them. Unlike many existing recommender attackers, which assume the dataset used to train the victim model is exposed to attackers, we consider a data-free setting, where training data are not accessible. Under this setting, we propose an API-based model extraction method via limited-budget synthetic data generation and knowledge distillation. We investigate state-of-the-art models for sequential recommendation and show their vulnerability under model extraction and downstream attacks. We perform attacks in two stages. (1) Model extraction: given different types of synthetic data and their labels retrieved from a black-box recommender, we extract the black-box model to a white-box model via distillation. (2) Downstream attacks: we attack the black-box model with adversarial samples generated by the white-box recommender. Experiments show the effectiveness of our data-free model extraction and downstream attacks on sequential recommenders in both profile pollution and data poisoning settings.

The performance of artificial intelligence (AI) algorithms in practice depends on the realism and correctness of the data, models, and feedback (labels or rewards) provided to the algorithm. This paper discusses methods for improving the realism and ecological validity of AI used for autonomous cyber defense by exploring the potential to use Inverse Reinforcement Learning (IRL) to gain insight into attacker actions, utilities of those actions, and ultimately decision points which cyber deception could thwart. The Tularosa study, as one example, provides experimental data of real-world techniques and tools commonly used by attackers, from which core data vectors can be leveraged to inform an autonomous cyber defense system.

Cyber deception considers the human aspects of an attacker in order to impede cyber attacks and improve Deceptive elements, including honeypots and decoys, security [17], which can also translate to advantages against were incorporated into the Microsoft CyberBattleSim automated attackers. Cyber deception aims to understand and experimentation and research platform influence an attacker even after they have already infiltrated [30]. The defensive capabilities of the deceptive a network, and ultimately to delay, deter, and disrupt their elements were tested using reinforcement attack. While some ML methods for detection in cybersecurity learning based attackers in the provided capture are still working on improving true-positive/false-positive the flag environment. The attacker's progress was rates, cyber deception technologies can often naturally act found to be dependent on the number and location as a high-confidence early warning mechanism.

Deep CNNs, though have achieved the state of the art performance in image classification tasks, remain a black-box to a human using them. There is a growing interest in explaining the working of these deep models to improve their trustworthiness. In this paper, we introduce a Posthoc Architecture-agnostic Concept Extractor (PACE) that automatically extracts smaller sub-regions of the image called concepts relevant to the black-box prediction. PACE tightly integrates the faithfulness of the explanatory framework to the black-box model. To the best of our knowledge, this is the first work that extracts class-specific discriminative concepts in a posthoc manner automatically. The PACE framework is used to generate explanations for two different CNN architectures trained for classifying the AWA2 and Imagenet-Birds datasets. Extensive human subject experiments are conducted to validate the human interpretability and consistency of the explanations extracted by PACE. The results from these experiments suggest that over 72% of the concepts extracted by PACE are human interpretable.

Evolutionary clustering algorithms have considered as the most popular and widely used evolutionary algorithms for minimising optimisation and practical problems in nearly all fields. In this thesis, a new evolutionary clustering algorithm star (ECA*) is proposed. Additionally, a number of experiments were conducted to evaluate ECA* against five state-of-the-art approaches. For this, 32 heterogeneous and multi-featured datasets were used to examine their performance using internal and external clustering measures, and to measure the sensitivity of their performance towards dataset features in the form of operational framework. The results indicate that ECA* overcomes its competitive techniques in terms of the ability to find the right clusters. Based on its superior performance, exploiting and adapting ECA* on the ontology learning had a vital possibility. In the process of deriving concept hierarchies from corpora, generating formal context may lead to a time-consuming process. Therefore, formal context size reduction results in removing uninterested and erroneous pairs, taking less time to extract the concept lattice and concept hierarchies accordingly. In this premise, this work aims to propose a framework to reduce the ambiguity of the formal context of the existing framework using an adaptive version of ECA*. In turn, an experiment was conducted by applying 385 sample corpora from Wikipedia on the two frameworks to examine the reduction of formal context size, which leads to yield concept lattice and concept hierarchy. The resulting lattice of formal context was evaluated to the original one using concept lattice-invariants. Accordingly, the homomorphic between the two lattices preserves the quality of resulting concept hierarchies by 89% in contrast to the basic ones, and the reduced concept lattice inherits the structural relation of the original one.

In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.

Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return responses with much lower latency but show inferior performance to the large-scale generative models since the conversation quality is bounded by the pre-defined response set. To take advantage of both approaches, we propose a new training method called G2R (Generative-to-Retrieval distillation) that preserves the efficiency of a retrieval model while leveraging the conversational ability of a large-scale generative model by infusing the knowledge of the generative model into the retrieval model. G2R consists of two distinct techniques of distillation: the data-level G2R augments the dialogue dataset with additional responses generated by the large-scale generative model, and the model-level G2R transfers the response quality score assessed by the generative model to the score of the retrieval model by the knowledge distillation loss. Through extensive experiments including human evaluation, we demonstrate that our retrieval-based conversation system trained with G2R shows a substantially improved performance compared to the baseline retrieval model while showing significantly lower inference latency than the large-scale generative models.

In this paper we outline a proposal for improving the governance of artificial intelligence (AI) by investing in government capacity to systematically measure and monitor the capabilities and impacts of AI systems. If adopted, this would give governments greater information about the AI ecosystem, equipping them to more effectively direct AI development and deployment in the most societally and economically beneficial directions. It would also create infrastructure that could rapidly identify potential threats or harms that could occur as a consequence of changes in the AI ecosystem, such as the emergence of strategically transformative capabilities, or the deployment of harmful systems. We begin by outlining the problem which motivates this proposal: in brief, traditional governance approaches struggle to keep pace with the speed of progress in AI. We then present our proposal for addressing this problem: governments must invest in measurement and monitoring infrastructure. We discuss this proposal in detail, outlining what specific things governments could focus on measuring and monitoring, and the kinds of benefits this would generate for policymaking. Finally, we outline some potential pilot projects and some considerations for implementing this in practice.

Kabul – When Ezmarai Ahmadi returned home from work on Sunday evening in Kabul, the usual gaggle of squealing children were waiting to greet him -- his sons and daughters, and a slew of nieces and nephews. He pulled his white sedan into the driveway of a modest house in Kwaja Burga, a densely populated neighborhood in the northwest of the Afghan capital, and handed the keys to his eldest son to park. Youngsters piled into the vehicle -- pretending the parking routine was an adventure -- while Ezmarai watched from the side. Then out of the blue Afghan sky, a missile came screeching down -- striking the car with a terrible force and obliterating the lives of 10 people in an instant. The United States said Sunday it had destroyed an explosive-laden vehicle in an air strike, thwarting a bid by the Islamic State to detonate a car bomb at Kabul airport. On Monday, it looked as if they could have made a terrible mistake.