Related papers: Collusion-Secure Watermarking for Sequential Data

Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models, yet is typically evaluated only under adversaries who attempt to evade detection or induce false positives at the level of individual…

Watermarking can detect sensor attacks in control systems by injecting a private signal into the control, whereby attacks are identified by checking the statistics of the sensor measurements and private signal. However, past approaches…

In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling from a generative model can reveal the watermark that was…

Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a cornerstone in privacy preservation efforts. However, the…

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

Whereas the embedding distortion, the payload and the robustness of digital watermarking schemes are well understood, the notion of security is still not completely well defined. The approach proposed in the last five years is too…

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…

Social networks have become an essential meeting point for millions of individuals willing to publish and consume huge quantities of heterogeneous information. Some studies have shown that the data published in these platforms may contain…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

Quantum indistinguishability of non-orthogonal quantum states is a valuable resource in quantum information applications such as cryptography and randomness generation. In this article, we present a sequential state-discrimination scheme…

We study protecting a user's data (images in this work) against a learner's unauthorized use in training neural networks. It is especially challenging when the user's data is only a tiny percentage of the learner's complete training set. We…

The emergence of distributed manufacturing ecosystems for electronic hardware involving untrusted parties has given rise to diverse trust issues. In particular, IP piracy, overproduction, and hardware Trojan attacks pose significant threats…

Though the sharing of medical data has the potential to lead to breakthroughs in health care, the sharing process itself exposes patients and health care providers to various risks. Patients face risks due to the possible loss in privacy or…

Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive…

The security of patient information is important during the transfer of medical data. A hybrid spatial domain watermarking algorithm that includes encryption, integrity protection and steganography is proposed to strengthen the information…

The wide deployment of Face Recognition (FR) systems poses privacy risks. One countermeasure is adversarial attack, deceiving unauthorized malicious FR, but it also disrupts regular identity verification of trusted authorizers, exacerbating…

Securing the Internet of Things (IoT) is a necessary milestone toward expediting the deployment of its applications and services. In particular, the functionality of the IoT devices is extremely dependent on the reliability of their message…

Collaborative Data Sharing raises a fundamental issue in distributed systems. Several strategies have been proposed for making shared data consistent between peers in such a way that the shared part of their local data become equal. Most of…

Privacy preserving in machine learning is a crucial issue in industry informatics since data used for training in industries usually contain sensitive information. Existing differentially private machine learning algorithms have not…