Related papers: Cooperating Attackers in Neural Cryptography
Deep learning is widely applied to modern problems through neural networks, but the growing computational and energy demands of these models have driven interest in more efficient approaches. Spiking Neural Networks (SNNs), the third…
Phishing attacks are the most common type of cyber-attacks used to obtain sensitive information and have been affecting individuals as well as organisations across the globe. Various techniques have been proposed to identify the phishing…
Federated Learning (FL) has emerged as a powerful paradigm for decentralized model training, yet it remains vulnerable to deep leakage (DL) attacks that reconstruct private client data from shared model updates. While prior DL methods have…
With the deepening of the digitization degree of financial business, financial fraud presents more complex and hidden characteristics, which poses a severe challenge to the risk prevention and control ability of financial institutions. At…
Graph modeling allows numerous security problems to be tackled in a general way, however, little work has been done to understand their ability to withstand adversarial attacks. We design and evaluate two novel graph attacks against a…
Secret sharing in user hierarchy represents a challenging area for research. Although a lot of work has already been done in this direc- tion, this paper presents a novel approach to share a secret among a hierarchy of users while…
We present novel perfect secrecy systems that provide immunity to spoofing attacks under equiprobable source probability distributions. On the theoretical side, relying on an existence result for $t$-designs by Teirlinck, our construction…
In this paper we revisit the mining strategies in proof of work based cryptocurrencies and propose two strategies, we call smart and smarter mining, that in many cases strictly dominate honest mining. In contrast to other known attacks,…
A large chunk of research on the security issues of neural networks is focused on adversarial attacks. However, there exists a vast sea of simpler attacks one can perform both against and with neural networks. In this article, we give a…
Cryptographic protocols are the cornerstone of security in distributed systems. The formal analysis of their properties is accordingly one of the focus points of the security community, and is usually split among two groups. In the first…
Cryptographic systems are derived using units in group rings. Combinations of types of units in group rings give units not of any particular type. This includes cases of taking powers of units and products of such powers and adds the…
We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and…
In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted…
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image…
Privacy preserving machine learning is an active area of research usually relying on techniques such as homomorphic encryption or secure multiparty computation. Recent novel encryption techniques for performing machine learning using deep…
In this paper we employ quantitative measurements of cognitive vulnerability triggers in phishing emails to predict the degree of success of an attack. To achieve this we rely on the cognitive psychology literature and develop an automated…
This paper considers the problem of security allocation in a networked control system under stealthy attacks. The system is comprised of interconnected subsystems represented by vertices. A malicious adversary selects a single vertex on…
While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…
Despite the promise of Federated Learning (FL) for privacy-preserving model training on distributed data, it remains susceptible to backdoor attacks. These attacks manipulate models by embedding triggers (specific input patterns) in the…
Federated Learning has rapidly expanded from its original inception to now have a large body of research, several frameworks, and sold in a variety of commercial offerings. Thus, its security and robustness is of significant importance.…