11 citations · 39 across the 30 of their papers we have counts for
30 papers
A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback
Yunian Pan, Tao Li, Quanyan Zhu
Mirror descent provides a geometric framework for learning in games, but its last-iterate behavior can fail in weakly stable regimes, where the dynamics may exhibit rotational or r…
Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundations
Tao Li, Quanyan Zhu
Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strat…
From Texts to Shields: Convergence of Large Language Models and Cybersecurity
Tao Li, Ya-Ting Yang, Yunian Pan +1
This report explores the convergence of large language models (LLMs) and cybersecurity, synthesizing interdisciplinary insights from network security, artificial intelligence, form…
Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective
Yunian Pan, Tao Li, Quanyan Zhu
Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control sy…
Transparent Tagging for Strategic Social Nudges on User-Generated Misinformation
Ya-Ting Yang, Tao Li, Quanyan Zhu
Social network platforms (SNP) rely heavily on user-generated content to attract users, yet they have limited control over content provision, which leads to misinformation. As coun…
Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data
Xinhong Xie, Tao Li, Quanyan Zhu
Text detoxification, a variant of style transfer tasks, finds useful applications in online social media. This work presents a fine-tuning method that only uses non-parallel data t…
Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
Tao Li, Henger Li, Yunian Pan +3
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to speci…
Multi-level Traffic-Responsive Tilt Camera Surveillance through Predictive Correlated Online Learning
Tao Li, Zilin Bian, Haozhe Lei +5
In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of survei…
On the Variational Interpretation of Mirror Play in Monotone Games
Yunian Pan, Tao Li, Quanyan Zhu
Mirror play (MP) is a well-accepted primal-dual multi-agent learning algorithm where all agents simultaneously implement mirror descent in a distributed fashion. The advantage of M…
Symbiotic Game and Foundation Models for Cyber Deception Operations in Strategic Cyber Warfare
Tao Li, Quanyan Zhu
We are currently facing unprecedented cyber warfare with the rapid evolution of tactics, increasing asymmetry of intelligence, and the growing accessibility of hacking tools. In th…
Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Games
Tao Li, Kim Hammar, Rolf Stadler +1
Asymmetric information stochastic games (AISGs) arise in many complex socio-technical systems, such as cyber-physical systems and IT infrastructures. Existing computational methods…
Automated Security Response through Online Learning with Adaptive Conjectures
Kim Hammar, Tao Li, Rolf Stadler +1
We study automated security response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed, non-stationary game. We rela…
Decision-Dominant Strategic Defense Against Lateral Movement for 5G Zero-Trust Multi-Domain Networks
Tao Li, Yunian Pan, Quanyan Zhu
Multi-domain warfare is a military doctrine that leverages capabilities from different domains, including air, land, sea, space, and cyberspace, to create a highly interconnected b…
Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning
Tao Li, Juan Guevara, Xinhong Xie +1
Offline reinforcement learning (RL) suffers from the distribution shift between the offline dataset and the online environment. In multi-agent RL (MARL), this distribution shift ma…
A First Order Meta Stackelberg Method for Robust Federated Learning
Yunian Pan, Tao Li, Henger Li +3
Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be no…
A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report)
Henger Li, Tianyi Xu, Tao Li +3
Recent research efforts indicate that federated learning (FL) systems are vulnerable to a variety of security breaches. While numerous defense strategies have been suggested, they…
Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning
Tao Li, Haozhe Lei, Hao Guo +4
Millimeter-wave (mmWave) communication is a vital component of future generations of mobile networks, offering not only high data rates but also precise beams, making it ideal for…
Is Stochastic Mirror Descent Vulnerable to Adversarial Delay Attacks? A Traffic Assignment Resilience Study
Yunian Pan, Tao Li, Quanyan Zhu
\textit{Intelligent Navigation Systems} (INS) are exposed to an increasing number of informational attack vectors, which often intercept through the communication channels between…
Designing Policies for Truth: Combating Misinformation with Transparency and Information Design
Ya-Ting Yang, Tao Li, Quanyan Zhu
Misinformation has become a growing issue on online social platforms (OSPs), especially during elections or pandemics. To combat this, OSPs have implemented various policies, such…
On the Price of Transparency: A Comparison between Overt Persuasion and Covert Signaling
Tao Li, Quanyan Zhu
Transparency of information disclosure has always been considered an instrumental component of effective governance, accountability, and ethical behavior in any organization or sys…
Scenario-Agnostic Zero-Trust Defense with Explainable Threshold Policy: A Meta-Learning Approach
Yunfei Ge, Tao Li, Quanyan Zhu
The increasing connectivity and intricate remote access environment have made traditional perimeter-based network defense vulnerable. Zero trust becomes a promising approach to pro…
Commitment with Signaling under Double-sided Information Asymmetry
Tao Li, Quanyan Zhu
Information asymmetry in games enables players with the information advantage to manipulate others' beliefs by strategically revealing information to other players. This work consi…
On the Resilience of Traffic Networks under Non-Equilibrium Learning
Yunian Pan, Tao Li, Quanyan Zhu
We investigate the resilience of learning-based \textit{Intelligent Navigation Systems} (INS) to informational flow attacks, which exploit the vulnerabilities of IT infrastructure…
Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation
Tao Li, Haozhe Lei, Quanyan Zhu
Powered by deep representation learning, reinforcement learning (RL) provides an end-to-end learning framework capable of solving self-driving (SD) tasks without manual designs. Ho…