15 citations · 34 across the 8 of their papers we have counts for
8 papers
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
Feiran Jia, Tong Wu, Xin Qin +1
Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhance…
Consensus in Complex Networks with Noisy Agents and Peer Pressure
Christopher Griffin, Anna Squicciarini, Feiran Jia
In this paper we study a discrete time consensus model on a connected graph with monotonically increasing peer-pressure and noise perturbed outputs masking a hidden state. We assum…
MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
Yiran Wu, Feiran Jia, Shaokun Zhang +7
Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language…
Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi +4
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution dur…
RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model
Hangzhi Guo, Feiran Jia, Jinghui Chen +2
Counterfactual (CF) explanations for machine learning (ML) models are preferred by end-users, as they explain the predictions of ML models by providing a recourse (or contrastive)…
Solving Structured Hierarchical Games Using Differential Backward Induction
Zun Li, Feiran Jia, Aditya Mate +4
From large-scale organizations to decentralized political systems, hierarchical strategic decision making is commonplace. We introduce a novel class of structured hierarchical game…
A Game-Theoretic Approach for Hierarchical Epidemic Control
Feiran Jia, Aditya Mate, Zun Li +5
We design and analyze a multi-level game-theoretic model of hierarchical policy interventions for epidemic control, such as those in response to the COVID-19 pandemic. Our model ca…
Blocking Adversarial Influence in Social Networks
Feiran Jia, Kai Zhou, Charles Kamhoua +1
While social networks are widely used as a media for information diffusion, attackers can also strategically employ analytical tools, such as influence maximization, to maximize th…