Picture for Shang-Tse Chen

Shang-Tse Chen

Annealing Self-Distillation Rectification Improves Adversarial Training

May 20, 2023
Yu-Yu Wu, Hung-Jui Wang, Shang-Tse Chen

* 10 pages + Appendix

Access Paper or Ask Questions

QCRS: Improve Randomized Smoothing using Quasi-Concave Optimization

Feb 01, 2023
Bo-Han Kung, Shang-Tse Chen

Figure 1 for QCRS: Improve Randomized Smoothing using Quasi-Concave Optimization

Figure 2 for QCRS: Improve Randomized Smoothing using Quasi-Concave Optimization

Figure 3 for QCRS: Improve Randomized Smoothing using Quasi-Concave Optimization

Figure 4 for QCRS: Improve Randomized Smoothing using Quasi-Concave Optimization

* 10 pages

Access Paper or Ask Questions

Fair Robust Active Learning by Joint Inconsistency

Sep 22, 2022
Tsung-Han Wu, Shang-Tse Chen, Winston H. Hsu

Figure 1 for Fair Robust Active Learning by Joint Inconsistency

Figure 2 for Fair Robust Active Learning by Joint Inconsistency

Figure 3 for Fair Robust Active Learning by Joint Inconsistency

Figure 4 for Fair Robust Active Learning by Joint Inconsistency

* 11 pages, 3 figures

Access Paper or Ask Questions

Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Aug 18, 2022
Hung-Jui Wang, Yu-Yu Wu, Shang-Tse Chen

Figure 1 for Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Figure 2 for Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Figure 3 for Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Figure 4 for Enhancing Targeted Attack Transferability via Diversified Weight Pruning

* 8 pages + 2 pages of references

Access Paper or Ask Questions

Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

Apr 18, 2019
Cory Cornelius, Shang-Tse Chen, Jason Martin, Duen Horng Chau

Figure 1 for Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

Figure 2 for Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

Figure 3 for Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

Figure 4 for Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA

* Submitted as talk proposal to Dependable and Secure Machine Learning (DSML '19)

Access Paper or Ask Questions

ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio

May 30, 2018
Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Li Chen, Michael E. Kounavis, Duen Horng Chau

Figure 1 for ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio

Figure 2 for ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio

* Demo paper; for supplementary video, see https://youtu.be/0W2BKMwSfVQ

Access Paper or Ask Questions