4 citations · 6 across the 5 of their papers we have counts for
7 papers
Engineering Robustness into Personal Agents with the AI Workflow Store
Roxana Geambasu, Mariana Raykova, Pierre Tholoniat +3
The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue tha…
A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
Trishita Tiwari, Ari Trachtenberg, G. Edward Suh
Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk i…
Sequence-Level Leakage Risk of Training Data in Large Language Models
Trishita Tiwari, G. Edward Suh
This work quantifies the risk of training data leakage from LLMs (Large Language Models) using sequence-level probabilities. Computing extraction probabilities for individual seque…
Information Flow Control in Machine Learning through Modular Model Architecture
Trishita Tiwari, Suchin Gururangan, Chuan Guo +7
In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is…
Case Study: Disclosure of Indirect Device Fingerprinting in Privacy Policies
Julissa Milligan, Sarah Scheffler, Andrew Sellars +3
Recent developments in online tracking make it harder for individuals to detect and block trackers. Some sites have deployed indirect tracking methods, which attempt to uniquely id…
Page Cache Attacks
Daniel Gruss, Erik Kraft, Trishita Tiwari +5
We present a new hardware-agnostic side-channel attack that targets one of the most fundamental software caches in modern computer systems: the operating system page cache. The pag…