58 citations · 98 across the 7 of their papers we have counts for
8 papers
Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees
Zhongnian Li, Shi Xu, Mengting Xu +2
Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selection and action generation d…
Complementary Labels Learning with Augmented Classes
Zhongnian Li, Jian Zhang, Mengting Xu +2
Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compar…
InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle
Mengting Xu, Tao Zhang, Zhongnian Li +1
Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the…
Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Mengting Xu, Tao Zhang, Zhongnian Li +1
Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrate…
MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack
Mengting Xu, Tao Zhang, Daoqiang Zhang
Deep neural networks are discovered to be non-robust when attacked by imperceptible adversarial examples, which is dangerous for it applied into medical diagnostic system that requ…
Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
Mengting Xu, Tao Zhang, Zhongnian Li +2
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown d…
Improving the Certified Robustness of Neural Networks via Consistency Regularization
Mengting Xu, Tao Zhang, Zhongnian Li +1
A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to b…
DISCO: Influence Maximization Meets Network Embedding and Deep Learning
Hui Li, Mengting Xu, Sourav S Bhowmick +3
Since its introduction in 2003, the influence maximization (IM) problem has drawn significant research attention in the literature. The aim of IM is to select a set of k users who…