A4S - Technical AI Sandbox
Posts by Collection
portfolio
publications
A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space
Published in Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), 2022
On the Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
Published in Proceedings of the 2023 IEEE Symposium on Security and Privacy (SP), 2023
Towards Adaptive Attacks on Constrained Tabular Machine Learning
Published in ICML 2024 Next Generation of AI Safety Workshop, 2024
On the Impact of Industrial Delays when Mitigating Distribution Drifts: an Empirical Study on Real-world Financial Systems
Published in KDD 2024 Discovering Drift Phenomena in Evolving Landscape Workshop, 2024
Studies the impact of industrial delays on mitigating distribution drifts in financial systems.
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Published in Advances in Neural Information Processing Systems (NeurIPS), 2024
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Published in Advances in Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS), 2024