Related papers: The Blob: provable incompressibility and traceabil…
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…
Due to their immutable log of information, blockchains can be considered as a transparency-enhancing technology. The immutability, however, also introduces threats and challenges with respect to privacy laws and illegal content. Introducing…
Software watermarking allows for embedding a mark into a piece of code, such that any attempt to remove the mark will render the code useless. Provably secure watermarking schemes currently seems limited to programs computing various…
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…
To accommodate the needs of large-scale distributed P2P systems, scalable data management strategies are required, allowing applications to efficiently cope with continuously growing, highly dis tributed data. This paper addresses the…
Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content provenance. Watermarking has emerged as a promising countermeasure, with existing work…
This paper presents a traitor-tracing technique based on the watermarking of digital documents (\pdf{} files in particular). The watermarking algorithm uses a chain of three separate techniques that work in synergy. The embedded payload can…
Due to the distributed nature of Federated Learning (FL) systems, each local client has access to the global model, which poses a critical risk of model leakage. Existing works have explored injecting watermarks into local models to enable…
With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…
As AI-generated images become widespread, reliable watermarking is essential for content verification, copyright enforcement, and combating disinformation. Existing techniques rely on heuristic approaches and lack formal guarantees of…
Traceability and auditability are key structures that are vital in supply chain management and construction. However, trust is the most important aspect of customers in these systems. Also, we have to rely on third parties to trade in…
Blockchain also known as a distributed ledger technology stores different transactions/operations in a chain of blocks in a distributed manner without needing a trusted third-party. Blockchain is proven to be immutable which helps for…
Decentralization for data storage is a challenging problem for blockchain-based solutions as the blocksize plays the key role for scalability. In addition, specific requirements of multimedia data calls for various changes in the blockchain…
Flow watermarks efficiently link packet flows in a network in order to thwart various attacks such as stepping stones. We study the problem of designing good flow watermarks. Earlier flow watermarking schemes mostly considered substitution…
In this paper we introduce a scheme for detecting manipulated audio and video. The scheme is a synthesis of blockchains, encrypted spread spectrum watermarks, perceptual hashing and digital signatures, which we call an Embedded Blockchain.…
Watermarking has emerged as a prominent technique for LLM-generated content detection by embedding imperceptible patterns. Despite supreme performance, its robustness against adversarial attacks remains underexplored. Previous work…
Unclonable encryption, first introduced by Broadbent and Lord (TQC'20), is a one-time encryption scheme with the following security guarantee: any non-local adversary (A, B, C) cannot simultaneously distinguish encryptions of two equal…
This work investigates the theoretical boundaries of creating publicly-detectable schemes to enable the provenance of watermarked imagery. Metadata-based approaches like C2PA provide unforgeability and public-detectability. ML techniques…