15 citations · 43 across the 9 of their papers we have counts for
9 papers
SoK: A Systems Perspective on Compound AI Threats and Countermeasures
Sarbartha Banerjee, Prateek Sahu, Mulong Luo +3
Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior res…
Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud
Marcin Chrapek, Anjo Vahldiek-Oberwagner, Marcin Spoczynski +3
Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically…
Making 'syscall' a Privilege not a Right
Fangfei Yang, Anjo Vahldiek-Oberwagner, Chia-Che Tsai +2
Browsers, Library OSes, and system emulators rely on sandboxes and in-process isolation to emulate system resources and securely isolate untrusted components. All access to system…
MeSHwA: The case for a Memory-Safe Software and Hardware Architecture for Serverless Computing
Anjo Vahldiek-Oberwagner, Mona Vij
Motivated by developer productivity, serverless computing, and microservices have become the de facto development model in the cloud. Microservices decompose monolithic application…
Cerberus: A Formal Approach to Secure and Efficient Enclave Memory Sharing
Dayeol Lee, Kevin Cheang, Alexander Thomas +7
Hardware enclaves rely on a disjoint memory model, which maps each physical address to an enclave to achieve strong memory isolation. However, this severely limits the performance…
The Endokernel: Fast, Secure, and Programmable Subprocess Virtualization
Bumjin Im, Fangfei Yang, Chia-Che Tsai +3
Commodity applications contain more and more combinations of interacting components (user, application, library, and system) and exhibit increasingly diverse tradeoffs between isol…
Swivel: Hardening WebAssembly against Spectre
Shravan Narayan, Craig Disselkoen, Daniel Moghimi +8
We describe Swivel, a new compiler framework for hardening WebAssembly (Wasm) against Spectre attacks. Outside the browser, Wasm has become a popular lightweight, in-process sandbo…
Privacy-Preserving Machine Learning in Untrusted Clouds Made Simple
Dayeol Lee, Dmitrii Kuvaiskii, Anjo Vahldiek-Oberwagner +1
We present a practical framework to deploy privacy-preserving machine learning (PPML) applications in untrusted clouds based on a trusted execution environment (TEE). Specifically,…
ERIM: Secure, Efficient In-process Isolation with Memory Protection Keys (MPK)
Anjo Vahldiek-Oberwagner, Eslam Elnikety, Nuno O. Duarte +3
Isolating sensitive state and data can increase the security and robustness of many applications. Examples include protecting cryptographic keys against exploits like OpenSSL's Hea…