相关论文: Puppy: A Publicly Verifiable Watermarking Protocol

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…

Autonomous and robotic systems are increasingly being trusted with sensitive activities with potentially serious consequences if that trust is broken. Runtime verification techniques present a natural source of inspiration for monitoring…

In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying dataset ownership or safeguarding private data from unauthorized use. However, these…

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…

Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a centralized trust model. This model forces users to reveal potentially sensitive text to a…

As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are…

Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This underscores the need for traceable TTS models-systems capable of…

Privacy concerns in machine learning systems have grown significantly with the increasing reliance on sensitive user data for training large-scale models. This paper introduces a novel framework combining Probably Approximately Correct…

A cryptographic protocol (CP) is a distributed algorithm designed to provide a secure communication in an insecure environment. CPs are used, for example, in electronic payments, electronic voting procedures, database access systems, etc.…

A niche corner of the Web3 world is increasingly making use of hardware-based Trusted Execution Environments (TEEs) to build decentralized infrastructure. One of the motivations to use TEEs is to go beyond the current performance…

The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and…

Data leakage from API responses has drawn wide attention. APIs are often not fully regulated, making them easy to abuse. One common solution is to embed watermarks into API responses for traceability. However, existing watermarking methods…

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

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…

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency…

We study statistical watermarking by formulating it as a hypothesis testing problem, a general framework which subsumes all previous statistical watermarking methods. Key to our formulation is a coupling of the output tokens and the…

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Trusted Execution Environments (TEEs) are designed to protect the privacy and integrity of data in use. They enable secure data processing and sharing in peer-to-peer networks, such as vehicular ad hoc networks of autonomous vehicles,…

We address the problem of efficiently verifying a commitment in a two-party computation. This addresses the scenario where a party P1 commits to a value $x$ to be used in a subsequent secure computation with another party P2 that wants to…

Programmable Logic Controllers (PLCs) are a core component of an Industrial Control System (ICS). However, if a PLC is compromised or the commands sent across a network from the PLCs are spoofed, consequences could be catastrophic. In this…