Related papers: Puppy: A Publicly Verifiable Watermarking Protocol

We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute to software development, watermarking has emerged as a…

Estimation of the Embedding capacity is an important problem specifically in reversible multi-pass watermarking and is required for analysis before any image can be watermarked. In this paper, we propose an efficient method for estimating…

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…

The rapid emergence of generative image models has led to the development of specialized watermarking techniques, particularly in-generation methods such as seed-based embedding. However, current evaluations in this area remain largely…

The sharing of public key information is central to the digital credential security model, but the existing Web PKI with its opaque Certification Authorities and synthetic attestations serves a very different purpose. We propose a new…

Getting access to labelled datasets in certain sensitive application domains can be challenging. Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target…

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing…

Large-scale data centers and cloud computing have turned system configuration into a challenging problem. Several widely-publicized outages have been blamed not on software bugs, but on configuration bugs. To cope, thousands of…

Distributed ledger systems (i.e., blockchains) have received a lot of attention. They promise to enable mutually untrusted participants to execute transactions while providing the immutability of the data and censorship resistance. Although…

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…

The Trusted Platform Module (TPM) version 2.0 provides a two-phase key exchange primitive which can be used to implement three widely-standardized authenticated key exchange protocols: the Full Unified Model, the Full MQV, and the SM2 key…

Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is very difficult to distinguish between the real images and…

We propose a maturity-based framework for certifying embodied AI systems through explicit measurement mechanisms. We argue that certifiable embodied AI requires structured assessment frameworks, quantitative scoring mechanisms, and methods…

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely…

The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non deterministic behaviour and distributed deployments of agents…

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

In recent years, watermarking generative tabular data has become a prominent framework to protect against the misuse of synthetic data. However, while most prior work in watermarking methods for tabular data demonstrate a wide variety of…

Cryptographic protocols aim at securing communications over insecure networks such as the Internet, where dishonest users may listen to communications and interfere with them. A secure communication has a different meaning depending on the…

Pufferfish privacy is a flexible generalization of differential privacy that allows to model arbitrary secrets and adversary's prior knowledge about the data. Unfortunately, designing general and tractable Pufferfish mechanisms that do not…

Watermarking has emerged as a crucial technique for detecting and attributing content generated by large language models. While recent advancements have utilized watermark ensembles to enhance robustness, prevailing methods typically…