Related papers: Cost-damage analysis of attack trees

Despite the success of deep learning-based algorithms, it is widely known that neural networks may fail to be robust. A popular paradigm to enforce robustness is adversarial training (AT), however, this introduces many computational and…

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

The critical assessment presented within this paper explores existing research pertaining to the Advanced Persistent Threat (APT) branch of cyber security, applying the knowledge extracted from this research to discuss, evaluate and…

Consider a network design application where we wish to lay down a minimum-cost spanning tree in a given graph; however, we only have stochastic information about the edge costs. To learn the precise cost of any edge, we have to conduct a…

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

We consider the well-studied problem of finding a spanning tree with minimum average distance between vertex pairs (called a MAD tree). This is a classic network design problem which is known to be NP-hard. While approximation algorithms…

The data arrangement problem on regular trees (DAPT) consists in assigning the vertices of a given graph G to the leaves of a d-regular tree T such that the sum of the pairwise distances of all pairs of leaves in T which correspond to edges…

Machine learning (ML) and artificial intelligence (AI) techniques have now become commonplace in software products and services. When threat modelling a system, it is therefore important that we consider threats unique to ML and AI…

Accurate state estimation is of paramount importance to maintain the power system operating in a secure and efficient state. The recently identified coordinated data injection attacks to meter measurements can bypass the current security…

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…

Decision trees are important both as interpretable models amenable to high-stakes decision-making, and as building blocks of ensemble methods such as random forests and gradient boosting. Their statistical properties, however, are not well…

Adversarial attacks are usually expressed in terms of a gradient-based operation on the input data and model, this results in heavy computations every time an attack is generated. In this work, we solidify the idea of representing…

It has become cognitive inertia to employ cross-entropy loss function in classification related tasks. In the untargeted attacks on graph structure, the gradients derived from the attack objective are the attacker's basis for evaluating a…

Fault tree analysis is a technique widely used in risk and reliability analysis of complex engineering systems given its deductive nature and relatively simple interpretation. In a fault tree, events are usually represented by a binary…

Network interdiction problems by deleting critical nodes have wide applications. However, node deletion is not always feasible in certain practical scenarios. We consider the maximum shortest path interdiction problem by upgrading nodes on…

Moving Target Defense (MTD) has emerged as a key technique in various security applications as it takes away the attacker's ability to perform reconnaissance for exploiting a system's vulnerabilities. However, most of the existing research…

With the great popularity of Graph Neural Networks (GNNs), their robustness to adversarial topology attacks has received significant attention. Although many attack methods have been proposed, they mainly focus on fixed-budget attacks,…

Association as a gift enables people do not have to mention something in completely straightforward words and allows others to understand what they intend to refer to. In this paper, we propose a chain association-based adversarial attack…

We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards,…

Blockchain systems, such as Ethereum, use an approach called "metering" to assign a cost to smart contract execution, an approach which is designed to incentivise miners to operate the network and protect it against DoS attacks. In the…