8 citations · 11 across the 4 of their papers we have counts for
5 papers
A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks
Farid Mafi, Saber Jafarpour, Mohammad Pirani
Adversarial attacks on graph neural networks (GNNs) have been studied as a model-centric optimization problem driven by gradients, learned policies, or meta-learning, with the grap…
Debugging WebAssembly? Put some Whamm on it!
Elizabeth Gilbert, Matthew Schneider, Zixi An +5
Debugging and monitoring programs are integral to engineering and deploying software. Dynamic analyses monitor applications through source code or IR injection, machine code or byt…
RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
Peter Yong Zhong, Siyuan Chen, Ruiqi Wang +4
Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or ma…
Can My Microservice Tolerate an Unreliable Database? Resilience Testing with Fault Injection and Visualization
Michael Assad, Christopher Meiklejohn, Heather Miller +1
In microservice applications, ensuring resilience during database or service disruptions constitutes a significant challenge. While several tools address resilience testing for ser…
Flexible Non-intrusive Dynamic Instrumentation for WebAssembly
Ben L. Titzer, Elizabeth Gilbert, Bradley Wei Jie Teo +3
A key strength of managed runtimes over hardware is the ability to gain detailed insight into the dynamic execution of programs with instrumentation. Analyses such as code coverage…