Related papers: Security Problems with Improper Implementations of…

Homomorphic encryption aims at allowing computations on encrypted data without decryption other than that of the final result. This could provide an elegant solution to the issue of privacy preservation in data-based applications, such as…

Current methods for authentication and key agreement based on public-key cryptography are vulnerable to quantum computing. We propose a novel approach based on artificial intelligence research in which communicating parties are viewed as…

LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks…

Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However,…

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

Advance in deep learning algorithms overshadows their security risk in software implementations. This paper discloses a set of vulnerabilities in popular deep learning frameworks including Caffe, TensorFlow, and Torch. Contrast to the small…

Designing a quantum key agreement (QKA) protocol is always a challenging task, because both the security and the fairness properties have to be considered simultaneously. Recently, Zhu et al. (Quantum Inf Process 14(11): 4245-4254) pointed…

Efficient identity management system has become one of the fundamental requirements for ensuring safe, secure, and transparent use of identifiable information and attributes. FIdM allows users to distribute their identity information across…

Deauthentication is an important component of any authentication system. The widespread use of computing devices in daily life has underscored the need for zero-effort deauthentication schemes. However, the quest for eliminating user effort…

Imagine a group of citizens willing to collectively contribute their personal data for the common good to produce socially useful information, resulting from data analytics or machine learning computations. Sharing raw personal data with a…

Secure multi-party computation-based machine learning, referred to as MPL, has become an important technology to utilize data from multiple parties with privacy preservation. While MPL provides rigorous security guarantees for the…

Fully Homomorphic Encryption (FHE) emerges one of the most promising solutions to privacy-preserving computing in an untrusted cloud. FHE can be implemented by various schemes, each of which has distinctive advantages, i.e., some are good…

We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. The commonly adopted compression schemes introduce…

This paper reports a detailed cryptanalysis of a recently proposed encryption scheme based on the logistic map. Some problems are emphasized concerning the key space definition and the implementation of the cryptosystem using floating-point…

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Encrypted deduplication combines encryption and deduplication to simultaneously achieve both data security and storage efficiency. State-of-the-art encrypted deduplication systems mainly build on deterministic encryption to preserve…

Identity-based encryption with equality test supporting flexible authorization (IBEET-FA) allows the equality test of underlying messages of two ciphertexts while strengthens privacy protection by allowing users (identities) to control the…

In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversarial examples, carefully designed adaptive attacks can bypass…

Adversaries with physical access to a target platform can perform cold boot or DMA attacks to extract sensitive data from the RAM. In response, several main-memory encryption schemes have been proposed to prevent such attacks. Also hardware…

In this paper, we propose a known-plaintext attack (KPA) method based on deep learning for traditional chaotic encryption scheme. We employ the convolutional neural network to learn the operation mechanism of chaotic cryptosystem, and…