相关论文: Scalable Edge Blocking Algorithms for Defending Ac…

The problem Defensive $\delta$-Covering, for some covering range $\delta > 0$, is a continuous facility location problem on undirected graphs where all edges have unit length. It is a generalization of Defensive Dominating Set and…

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge…

In a graph G, a k-attack A is any set of at most k vertices and l-defense D is a set of at most l vertices. We say that defense D counters attack A if each a in A can be matched to a distinct defender d in D with a equal to d or a adjacent…

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

The rise of advanced persistent threats (APTs) has marked a significant cybersecurity challenge, characterized by sophisticated orchestration, stealthy execution, extended persistence, and targeting valuable assets across diverse sectors.…

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of…

Given an undirected graph G, the edge orientation problem asks for assigning a direction to each edge to convert G into a directed graph. The aim is to minimize the maximum out degree of a vertex in the resulting directed graph. This…

We study a security game over a network played between a $defender$ and $k$ $attackers$. Every attacker chooses, probabilistically, a node of the network to damage. The defender chooses, probabilistically as well, a connected induced…

Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. However, recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the…

While intrusion detection systems form the first line-of-defense against cyberattacks, they often generate an overwhelming volume of alerts, leading to alert fatigue among security operations center (SOC) analysts. Alert-driven attack…

Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Although there are several…

This article focuses on the security assessment of electricity Distribution Networks (DNs) with vulnerable Distributed Energy Resource (DER) nodes. The adversary model is simultaneous compromise of DER nodes by strategic manipulation of…

Defending computer networks from cyber attack requires timely responses to alerts and threat intelligence. Decisions about how to respond involve coordinating actions across multiple nodes based on imperfect indicators of compromise while…

Adversarial attacks to graph analytics are gaining increased attention. To date, two lines of countermeasures have been proposed to resist various graph adversarial attacks from the perspectives of either graph per se or graph neural…

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and…

In light of rising cybersecurity threats, data center providers face growing pressure to protect their own management infrastructure from Distributed Denial-of-Service (DDoS) attacks. While tenant-managed cages generally fall outside the…

Security protocols are often found to be flawed after their deployment. We present an approach that aims at the neutralization or mitigation of the attacks to flawed protocols: it avoids the complete dismissal of the interested protocol and…

In response to the rapidly evolving nature of adversarial attacks against visual classifiers, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes…

Score-based query attacks pose a serious threat to deep learning models by crafting adversarial examples (AEs) using only black-box access to model output scores, iteratively optimizing inputs based on observed loss values. While recent…

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…