16 citations · 96 across the 22 of their papers we have counts for
22 papers
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Xiangning Lin, Shenzhe Zhu, Shu Yang +23
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are r…
Permission Manifests for Web Agents
Samuele Marro, Alan Chan, Xinxing Ren +12
The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conven…
Identity Management for Agentic AI: The new frontier of authorization, authentication, and security for an AI agent world
Tobin South, Subramanya Nagabhushanaradhya, Ayesha Dissanayaka +18
The rapid rise of AI agents presents urgent challenges in authentication, authorization, and identity management. Current agent-centric protocols (like MCP) highlight the demand fo…
Private, Verifiable, and Auditable AI Systems
Tobin South
The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the co…
Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
Nicola Croce, Tobin South
The Model Context Protocol (MCP) represents a significant advancement in AI-tool integration, enabling seamless communication between AI agents and external services. However, this…
The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets
Shenzhe Zhu, Jiao Sun, Yi Nian +3
AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a fut…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…
Authenticated Delegation and Authorized AI Agents
Tobin South, Samuele Marro, Thomas Hardjono +5
The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know…
Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep +40
Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established data…
Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee +46
General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we…
Open Problems in Technical AI Governance
Anka Reuel, Ben Bucknall, Stephen Casper +30
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at…
Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
Shayne Longpre, Robert Mahari, Naana Obeng-Marnu +5
New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have…
Verifiable evaluations of machine learning models using zkSNARKs
Tobin South, Alexander Camuto, Shrey Jain +5
In a world of increasing closed-source commercial machine learning models, model evaluations from developers must be taken at face value. These benchmark results-whether over task…
Don't forget private retrieval: distributed private similarity search for large language models
Guy Zyskind, Tobin South, Alex Pentland
While the flexible capabilities of large language models (LLMs) allow them to answer a range of queries based on existing learned knowledge, information retrieval to augment genera…
zkTax: A pragmatic way to support zero-knowledge tax disclosures
Alex Berke, Tobin South, Robert Mahari +2
Tax returns contain key financial information of interest to third parties: public officials are asked to share financial data for transparency, companies seek to assess the financ…
Open Problems in DAOs
Joshua Tan, Tara Merk, Sarah Hubbard +26
Decentralized autonomous organizations (DAOs) are a new, rapidly-growing class of organizations governed by smart contracts. Here we describe how researchers can contribute to the…
Building a healthier feed: Private location trace intersection driven feed recommendations
Tobin South, Nick Lothian, Alex "Sandy" Pentland
The physical environment you navigate strongly determines which communities and people matter most to individuals. These effects drive both personal access to opportunities and the…
Information flow estimation: a study of news on Twitter
Tobin South, Bridget Smart, Matthew Roughan +1
News media has long been an ecosystem of creation, reproduction, and critique, where news outlets report on current events and add commentary to ongoing stories. Understanding the…
Are we always in strife? A longitudinal study of the echo chamber effect in the Australian Twittersphere
Mehwish Nasim, Derek Weber, Tobin South +4
Contrary to expectations that the increased connectivity offered by the internet and particularly Online Social Networks (OSNs) would result in broad consensus on contentious issue…
Popularity and Centrality in Spotify Networks: Critical transitions in eigenvector centrality
Tobin South, Matthew Roughan, Lewis Mitchell
The modern age of digital music access has increased the availability of data about music consumption and creation, facilitating the large-scale analysis of the complex networks th…
Complex contagion features without social reinforcement in a model of social information flow
Tyson Pond, Saranzaya Magsarjav, Tobin South +2
Contagion models are a primary lens through which we understand the spread of information over social networks. However, simple contagion models cannot reproduce the complex featur…
How the Avengers assemble: Ecological modelling of effective cast sizes for movies
Matthew Roughan, Lewis Mitchell, Tobin South
The number of characters in a movie is an interesting feature. However, it is non-trivial to measure directly. Naive metrics such as the number of credited characters vary wildly.…