Related papers: Extension of Overbeck's Attack for Gabidulin Based…

This paper studies kernelized bandits (also known as Gaussian process bandits) in an adversarial environment, where the reward functions in a known reproducing kernel Hilbert space (RKHS) may be adversarially chosen at each round. We show…

Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph learning tasks. However, recent studies show that GNNs are vulnerable to both test-time evasion and training-time poisoning attacks that perturb the graph…

Automating arrhythmia detection from ECG requires a robust and trusted system that retains high accuracy under electrical disturbances. Many machine learning approaches have reached human-level performance in classifying arrhythmia from…

Graph-based classification methods are widely used for security and privacy analytics. Roughly speaking, graph-based classification methods include collective classification and graph neural network. Evading a graph-based classification…

We investigate implementations of biometric cryptosystems protecting fingerprint templates (which are mostly based on the fuzzy vault scheme by Juels and Sudan in 2002) with respect to the security they provide. We show that attacks taking…

Blockchain technology has evolved through many changes and modifications, such as smart-contracts since its inception in 2008. The popularity of a blockchain system is due to the fact that it offers a significant security advantage over…

Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients…

We investigate security properties of the Anshel-Anshel-Goldfeld commutator key-establishment protocol used with certain polycyclic groups. We show that despite low success of the length based attack the protocol can be broken by a…

In recent years, graph neural networks (GNNs) have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that current GNNs are susceptible to malicious adversarial attacks.…

Person re-identification (re-ID) has attracted much attention recently due to its great importance in video surveillance. In general, distance metrics used to identify two person images are expected to be robust under various appearance…

In this paper we analyze different biometric authentication protocols considering an internal adversary. Our contribution takes place at two levels. On the one hand, we introduce a new comprehensive framework that encompasses the various…

In this paper we consider cryptographic applications of the arithmetic on the hyperoctahedral group. On an appropriate subgroup of the latter, we particularly propose to construct public key cryptosystems based on the discrete logarithm.…

We propose a novel approach to improving software security called Cryptographic Path Hardening, which is aimed at hiding security vulnerabilities in software from attackers through the use of provably secure and obfuscated cryptographic…

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Strong attacks against quantum key distribution use quantum memories and quantum gates to attack directly the final key. In this paper we extend a novel security result recently obtained, to demonstrate proofs of security against a wide…

In this paper, we investigate the rank-metric codes which are proposed by Delsarte and Gabidulin to be complementary dual codes. We point out the relationship between Delsarte complementary dual codes and Gabidulin complementary dual codes.…

We study the robustness against adversarial examples of kNN classifiers and classifiers that combine kNN with neural networks. The main difficulty lies in the fact that finding an optimal attack on kNN is intractable for typical datasets.…

Quantum Key Distribution or QKD provides symmetric key distribution using the quantum mechanics/channels with new security properties. The security of QKD relies on the difficulty of the quantum state discrimination problem. We discover…

Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number…

Recent studies show that Graph Neural Networks (GNNs) are vulnerable to adversarial attack, i.e., an imperceptible structure perturbation can fool GNNs to make wrong predictions. Some researches explore specific properties of clean graphs…