Related papers: Publicly-Verifiable Deletion via Target-Collapsing…

Modern face recognition systems utilize deep neural networks to extract salient features from a face. These features denote embeddings in latent space and are often stored as templates in a face recognition system. These embeddings are…

We study uncloneable quantum encryption schemes for classical messages as recently proposed by Broadbent and Lord. We focus on the information-theoretic setting and give several limitations on the structure and security of these schemes:…

We propose the first continuous-variable (CV) unclonable encryption scheme, extending the paradigm of quantum encryption of classical messages (QECM) to CV systems. In our construction, a classical message is first encrypted classically and…

In the classical setting, public-key encryption requires randomness in order to be secure against a forward search attack, whereby an adversary compares the encryption of a guess of the secret message with that of the actual secret message.…

Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To…

Inference problems with conjectured statistical-computational gaps are ubiquitous throughout modern statistics, computer science and statistical physics. While there has been success evidencing these gaps from the failure of restricted…

We give new proofs for the hardness amplification of efficiently samplable predicates and of weakly verifiable puzzles which generalize to new settings. More concretely, in the first part of the paper, we give a new proof of Yao's XOR-Lemma…

This article bridges the gap between two topics used in sharing an encryption key: (i) Key Consolidation, i.e., extracting two identical strings of bits from two information sources with similarities (common randomness). (ii) Quantum-safe…

Here, we investigate the security of the practical one-way CVQKD and CV-MDI-QKD systems under laser seeding attack. In particular, Eve can inject a suitable light into the laser diodes of the light source modules in the two kinds of…

LiDAR-based 3D object detection and classification is crucial for autonomous driving. However, real-time inference from extremely sparse 3D data is a formidable challenge. To address this problem, a typical class of approaches transforms…

In this letter, as a proof of concept, we propose a deep learning-based approach to attack the chaos-based image encryption algorithm in \cite{guan2005chaos}. The proposed method first projects the chaos-based encrypted images into the…

We propose a novel method for securely training the vision transformer (ViT) with sensitive data shared from multiple clients similar to privacy-preserving federated learning. In the proposed method, training images are independently…

The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks. Trust among these financial institutions…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

A Publicly Verifiable Secret Sharing (PVSS) scheme allows anyone to verify the validity of the shares computed and distributed by a dealer. The idea of PVSS was introduced by Stadler in [18] where he presented a PVSS scheme based on…

Threshold Homomorphic Encryption (Threshold HE) is a good fit for implementing private federated average aggregation, a key operation in Federated Learning (FL). Despite its potential, recent studies have shown that threshold schemes…

In this paper we propose a tokenization algorithm of Reversible Hybrid type, as defined in PCI DSS guidelines for designing a tokenization solution, based on a block cipher with a secret key and (possibly public) additional input. We…

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or…

In this paper, we introduce PrivDFS, a distributed feature-sharing framework for input-private inference in image classification. A single holistic intermediate representation in split inference gives diffusion-based Data Reconstruction…

Data hiding is one widely used approach for protecting authentication and ownership. Most multimedia content like images and videos are transmitted or saved in the compressed form. This kind of lossy compression, such as JPEG, can destroy…