22 papers · ranked by Valyu relevance
Víctor Mayoral-Vilches, María Sanz-Gómez, Francesco Balassone, Stefan Rass + 5 more
AI-driven penetration testing now executes thousands of actions per hour but still lacks the strategic intuition humans apply in competitive security. To build cybersecurity superintelligence–Cybersecurity AI exceeding best human capability—such strategic intuition must be embedded into agentic reasoning processes. We…
Huy Q. Ngo
Microsoft's Active Directory (AD) is a directory service that enables the IT admin to manage security permissions and control access within a Windows domain network. As a core management system in many of organisation, AD has become a primary target for adversaries. While many solutions for hardening attack graphs…
Zhen Wang, Kristen Moore, Qin Wang, Guangsheng Yu + 6 more
Large Language Models (LLMs) show promise for supporting decision-making in cybersecurity, but their reliability in high-stakes, time-evolving environments remains limited due to hallucinations, poor temporal reasoning, and shallow grounding in system context. We introduce DEFENGRAPH, an LLM-driven assistant designed…
Sheng, Qi
Provenance analysis based on system audit data has emerged as a fundamental approach for investigating Advanced Persistent Threat (APT) attacks. Due to the high concealment and long-term persistence of APT attacks, they are only represented as a minimal part of the critical path in the provenance graph. While existing…
Jie Huang, Qiaoyan Sun, Na Zhang, Meizhu Zheng + 1 more
Hypergraph Neural Networks (HGNNs) have become an important tool for processing complex structured data due to their ability to model higher-order associative relationships. However, the inherent adversarial vulnerabilities of HGNNs may raise serious security risks. The associated risks are far more pronounced in…
Fan Yang, Binyan Xu, Di Tang, Kehuan Zhang
GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph patterns or node features, and thus can be circumvented by adaptive attackers. We propose PRAETORIAN, a new defense that targets intrinsic…
Muhammed Rafeeq War, Aqsa Sayeed, Shahid Ahmad Wani, Ayoob Lone + 2 more
The increasing prevalence of robotic systems across diverse domains has undoubtedly delivered numerous advantages. However, this proliferation has also exposed these systems to potential security threats, with the ability to cause significant human and financial losses. In this study we propose a proactive approach to…
Mikel Ferrer-Oliva, José-Amelio Medina-Merodio, José-Javier Martínez-Herraiz, Carlos Cilleruelo-Rodríguez + 2 more
The increasing scale and operational complexity of cyberattacks have exposed the limitations of static taxonomies for representing multistage threat scenarios. This study addresses the need for more flexible classification models by proposing a relational taxonomy of cyberattacks grounded in documented incidents.…
Tong Zhao, Wei Yang, Yu Yao, Tat-Hean Gan
Industrial sensor systems are increasingly vulnerable to both physical anomalies and cyberattacks, while their collected time series typically present complex periodic and non-stationary characteristics, along with dynamic spatial dependencies among sensors. To address these issues, this paper proposes a dual-branch…
Aravindhan Manivannan, Anthoniraj Amalanathan
Due to being reactive in nature, most network security frameworks focus on identifying attacks as they take place or reconstructing intrusion sequences once they have already occurred. This paper presents GeoGuard-PTI, an innovative Geo-Temporal Predictive Threat Intelligence framework designed to shift that paradigm…
Mohammad Khalaf Khreasat, Gabriel Villarrubia González, Linheng Li
A central open question in automotive intrusion detection is not merely whether relational representations of Controller Area Network (CAN) traffic improve performance, but which aspects of CAN traffic structure transfer robustly across attacks and which do not transfer across vehicle platforms, and why. To investigate…
Jacob Blindenbach, Shaunak Soni, Gamze Gürsoy
The human pangenome reference, often represented as a graph, promises to capture genetic diversity across populations, but open release of individual haplotypes raises significant privacy concerns, including risks of re-identification and inference of sensitive traits. To address these challenges, we introduce…
Authors not listed
Transition-state (TS) identification for bimolecular liquid-phase reactions is notoriously sensitive to the initial spatial arrangement of reactants, making automated searches difficult, especially in solvation where conformational effects dominate barrier heights. We address this gap with a fully automated, heuristic…
Authors not listed
Computational methods for predictive modeling have been increasingly utilized in the early stages of drug discovery to supplement high-throughput screening. The advent of highly efficient and complex machine learning architectures necessitates new methods of collating the plethora of topological, geometrical, and…
Aris Karatzikos, Aggeliki Vasilopoulou, Candace SY Chan, Ioannis Mouratidis + 1 more
Genomic foundation models can dramatically accelerate biological research by learning general-purpose representations of genomic data that transfer across tasks, enabling researchers to predict variant effects, regulatory elements, and molecular function, among others. To safeguard against potential biosecurity threats…
Hakime Öztürk, Tejumade Afonja, Joonas Jälkö, Ruta Binkyte + 18 more
The synthesis of anonymized data derived from real-world cohorts offers a promising strategy for regulatory-compliant and privacy-preserving biological data sharing, potentially facilitating model development that can improve predictive performance. However, the extent to which generative models can preserve biological…
Siddharth Sabata, Russell Schwartz
Tumor phylogenies — rooted trees encoding clonal ancestry and mutation acquisition — are central to understanding cancer evolution, yet generating realistic phylogenies remains challenging. We investigate whether discrete graph diffusion can learn the structural constraints of tumor phylogenies directly from data.…
Authors not listed
We present a new method for fingerprint- ing atomic configurations relevant to ML-IAM training and application, utilizing the ChIMES descriptor. These fingerprints enable rigor- ous analysis of statistical distinguishability be- tween configurations. Sample applications in- clude assessing diversity within ML-IAP…
Steven Golob, Patrick McKeever, Sikha Pentyala, Martine De Cock + 1 more
Single-cell RNA sequencing (scRNA-seq) data is subject to strict access control due to its sensitive nature, motivating the use of synthetic data generation (SDG) for privacy-preserving data sharing. We present the first adversarial privacy attack that performs meaningfully above random guessing against…
Daniel M. Gonçalves, André Patrício, Rafael S. Costa, Rui Henriques
The growing availability and complexity of omics data have driven the development of specialized algorithms for modeling molecular systems. Although graph-based learning methods effectively represent biological interactions, they often neglect the statistical information embedded in node and edge annotations. To…
Authors not listed
High-entropy layered double hydroxides (HE-LDHs) have shown great potential in oxygen evolution reaction (OER) catalysis due to their tunable compositions and electronic structures. However, the synergistic effects between multiple vacancies, such as metal and oxygen vacancies, remain poorly understood and challenging…
Authors not listed
Graph Neural Networks (GNNs) are powerful tools for molecular property prediction, but they are not magic. When applied to molecules unlike their training data, they produce unreliable predictions that are difficult to detect. The Applicability Domain (AD) concept addresses this by defining regions of chemical space…