Search Results for author:
Found 7 papers, 3 papers with code
Adversarial Attack Generation Empowered by Min-Max Optimization
In this paper, we show how a general framework of min-max optimization over multiple domains can be leveraged to advance the design of different types of adversarial attacks.
Towards A Unified Min-Max Framework for Adversarial Exploration and Robustness
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness against norm-ball bounded input perturbations.
An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms
Existing approximation algorithms, although achieving great improvement over the exact algorithm, relies on retraining models for multiple times, thus remaining limited when applied to larger-scale learning tasks and real-world datasets.
Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption.
On Adversarial Robustness of Point Cloud Semantic Segmentation
As such, we present a comparative study of PCSS robustness.
Maestro: A Gamified Platform for Teaching AI Robustness
We assessed Maestro's influence on students' engagement, motivation, and learning success in robust AI.
AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems.
