6 citations · 12 across the 10 of their papers we have counts for
11 papers
Agent Security is a Systems Problem
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants…
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly int…
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
Agent Learning via Early Experience
Kai Zhang, Xiangchao Chen, Bo Liu +27
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents fro…
Training Language Models to Generate Quality Code with Program Analysis Feedback
Feng Yao, Zilong Wang, Liyuan Liu +7
Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g.,…
Matching Skeleton-based Activity Representations with Heterogeneous Signals for HAR
Shuheng Li, Jiayun Zhang, Xiaohan Fu +3
In human activity recognition (HAR), activity labels have typically been encoded in one-hot format, which has a recent shift towards using textual representations to provide contex…
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
Andrey Labunets, Nishit V. Pandya, Ashish Hooda +2
We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an…
Imprompter: Tricking LLM Agents into Improper Tool Use
Xiaohan Fu, Shuheng Li, Zihan Wang +4
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more gen…
Ventilation and Temperature Control for Energy-efficient and Healthy Buildings: A Differentiable PDE Approach
Yuexin Bian, Xiaohan Fu, Rajesh K. Gupta +1
In this paper, we introduce a novel framework for building learning and control, focusing on ventilation and thermal management to enhance energy efficiency. We validate the perfor…
Physics-Informed Data Denoising for Real-Life Sensing Systems
Xiyuan Zhang, Xiaohan Fu, Diyan Teng +9
Sensors measuring real-life physical processes are ubiquitous in today's interconnected world. These sensors inherently bear noise that often adversely affects performance and reli…
Misusing Tools in Large Language Models With Visual Adversarial Examples
Xiaohan Fu, Zihan Wang, Shuheng Li +4
Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security ri…