Related papers: TITAN: Graph-Executable Reasoning for Cyber Threat…

Developing models that can learn to reason is a notoriously challenging problem. We focus on reasoning in relational domains, where the use of Graph Neural Networks (GNNs) seems like a natural choice. However, previous work has shown that…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Text-to-SQL is a critical task in natural language processing that aims to transform natural language questions into accurate and executable SQL queries. In real-world scenarios, these reasoning tasks are often accompanied by complex…

In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning…

The challenge of decision-making under uncertainty in information security has become increasingly important, given the unpredictable probabilities and effects of events in the ever-changing cyber threat landscape. Cyber threat intelligence…

Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation…

Disruptions at critical logistics nodes pose severe risks to global supply chains, yet existing risk prediction systems typically prioritize forecasting accuracy without providing operationally interpretable early warnings. This paper…

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate…

Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial manipulation of the thought chain itself, known as…

Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM). Although existing studies have predominantly focused on…

We study deceptive fairness attacks on graphs to answer the following question: How can we achieve poisoning attacks on a graph learning model to exacerbate the bias deceptively? We answer this question via a bi-level optimization problem…

The increasingly sophisticated and growing number of threat actors along with the sheer speed at which cyber attacks unfold, make timely identification of attacks imperative to an organisations' security. Consequently, persons responsible…

The investigation of the terrorist attack is a time-critical task. The investigators have a limited time window to diagnose the organizational background of the terrorists, to run down and arrest the wire-pullers, and to take an action to…

Graph knowledge models and ontologies are very powerful modeling and re asoning tools. We propose an effective approach to model network attacks and attack prediction which plays important roles in security management. The goals of this…

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep…

Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natural language…

Rationale discovery is defined as finding a subset of the input data that maximally supports the prediction of downstream tasks. In the context of graph machine learning, graph rationale is defined to locate the critical subgraph in the…

Cyber attacks have become a vital threat to connected autonomous vehicles in intelligent transportation systems. Cyber threat intelligence, as the collection of cyber threat information, provides an ideal approach for responding to emerging…

Modern 5G-Advanced and emerging 6G cloud-native telecom architectures encounter unprecedented hyper-complexity, multi-layered threat vectors, and fluid structural topologies. Managing infrastructure security using manual, imperative…

A natural image usually conveys rich semantic content and can be viewed from different angles. Existing image description methods are largely restricted by small sets of biased visual paragraph annotations, and fail to cover rich underlying…