90 citations · 254 across the 23 of their papers we have counts for
12 papers · 1 filter
Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks
Franziska Roesner, Tadayoshi Kohno
Thompson's "Reflections on Trusting Trust" showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source reproduces the Trojan. Today,…
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
Alexandra E. Michael, Franziska Roesner
As AI agents grow in prevalence, so too do their risks to users, creating a need for robust and usable systems for agent permissions. Many recent proposals implement product-level…
Extending the Formalism and Theoretical Foundations of Cryptography to AI
Federico Villa, F. Betül Durak, Tadayoshi Kohno +2
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents…
Towards Automating Data Access Permissions in AI Agents
Yuhao Wu, Ke Yang, Franziska Roesner +3
As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing m…
SoK: Advances and Open Problems in Web Tracking
Yash Vekaria, Yohan Beugin, Shaoor Munir +11
Web tracking is a pervasive and opaque practice that enables personalized advertising, retargeting, and conversion tracking. Over time, it has evolved into a sophisticated and inva…
SoK (or SoLK?): On the Quantitative Study of Sociodemographic Factors and Computer Security Behaviors
Miranda Wei, Jaron Mink, Yael Eiger +3
Researchers are increasingly exploring how gender, culture, and other sociodemographic factors correlate with user computer security and privacy behaviors. To more holistically und…
IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
Yuhao Wu, Franziska Roesner, Tadayoshi Kohno +2
Large language models (LLMs) extended as systems, such as ChatGPT, have begun supporting third-party applications. These LLM apps leverage the de facto natural language-based autom…
LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins
Umar Iqbal, Tadayoshi Kohno, Franziska Roesner
Large language model (LLM) platforms, such as ChatGPT, have recently begun offering an app ecosystem to interface with third-party services on the internet. While these apps extend…
Tracking, Profiling, and Ad Targeting in the Alexa Echo Smart Speaker Ecosystem
Umar Iqbal, Pouneh Nikkhah Bahrami, Rahmadi Trimananda +7
Smart speakers collect voice commands, which can be used to infer sensitive information about users. Given the potential for privacy harms, there is a need for greater transparency…
Making Distributed Mobile Applications SAFE: Enforcing User Privacy Policies on Untrusted Applications with Secure Application Flow Enforcement
Adriana Szekeres, Irene Zhang, Katelin Bailey +6
Today's mobile devices sense, collect, and store huge amounts of personal information, which users share with family and friends through a wide range of applications. Once users gi…
COVID-19 Contact Tracing and Privacy: Studying Opinion and Preferences
Lucy Simko, Ryan Calo, Franziska Roesner +1
There is growing interest in technology-enabled contact tracing, the process of identifying potentially infected COVID-19 patients by notifying all recent contacts of an infected p…
Challenges and New Directions in Augmented Reality, Computer Security, and Neuroscience -- Part 1: Risks to Sensation and Perception
Stefano Baldassi, Tadayoshi Kohno, Franziska Roesner +1
Rapidly advancing AR technologies are in a unique position to directly mediate between the human brain and the physical world. Though this tight coupling presents tremendous opport…