Related papers: Continuous Encryption Functions for Security Over …

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

Privacy-preserving inference of convolutional neural networks (CNNs) using homomorphic encryption has emerged as a promising approach for enabling secure machine learning in untrusted environments. In our previous work, we introduced a…

Artificial intelligence (AI) increasingly powers sensitive applications in domains such as healthcare and finance, relying on both linear operations (e.g., matrix multiplications in large language models) and non-linear operations (e.g.,…

Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable…

Fully homomorphic encryption (FHE) has experienced significant development and continuous breakthroughs in theory, enabling its widespread application in various fields, like outsourcing computation and secure multi-party computing, in…

Web attacks, i.e. attacks exclusively using the HTTP protocol, are rapidly becoming one of the fundamental threats for information systems connected to the Internet. When the attacks suffered by web servers through the years are analyzed,…

We present information-theoretic definitions and results for analyzing symmetric-key encryption schemes beyond the perfect secrecy regime, i.e. when perfect secrecy is not attained. We adopt two lines of analysis, one based on lossless…

Prior work has demonstrated that functionally correct yet vulnerable outputs arise systematically in threat-oriented settings, where adversarial or implicit channels are used to induce security failures in code agents and automated patching…

In this paper, we analyze existing feature selection methods to identify the key elements of network traffic data that allow intrusion detection. In addition, we propose a new feature selection method that addresses the challenge of…

Forward Secrecy (FS) is a security property in key-exchange algorithms which guarantees that a compromise in the secrecy of a long-term private-key does not compromise the secrecy of past session keys. With a growing awareness of long-term…

Vector Stream Cipher (VSC) is a stream cipher which consists of permutation polynomial over a ring of modulo $2^w$. The algorithm for generating key stream is very simple and the encryption is very fast. Some theoretical attacks for VSC…

Homomorphic encryption (HE) has found extensive utilization in federated learning (FL) systems, capitalizing on its dual advantages: (i) ensuring the confidentiality of shared models contributed by participating entities, and (ii) enabling…

With the rapid advancements in machine learning, models have become increasingly capable of learning and making predictions in various industries. However, deploying these models in critical infrastructures presents a major challenge, as…

Support Vector Machines (SVMs) are among the most popular classification techniques adopted in security applications like malware detection, intrusion detection, and spam filtering. However, if SVMs are to be incorporated in real-world…

Federated learning is a learning method for training models over multiple participants without directly sharing their raw data, and it has been expected to be a privacy protection method for training data. In contrast, attack methods have…

Website fingerprinting (WF) attacks identify the websites visited over anonymized connections by analyzing patterns in network traffic flows, such as packet sizes, directions, or interval times using a machine learning classifier. Previous…

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNN) possible. However, the performance of these methods remain limited by their heavy…

Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…

In this paper, after reviewing the main points of image encryption and threshold function, we introduce the methods of chaotic image encryption based on pseudorandom bit padding that the bits be generated by the novel generalized threshold…

Parameter estimation is a critical step in continuous-variable quantum key distribution (CV-QKD), especially in the finite-size regime where worst-case confidence intervals can significantly reduce the achievable secret-key rate. We provide…