activity
20162024
most citedEnhancing Targeted Attack Transferability via Diversified Weight Pruning

1 citations · 3 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2024

Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation

Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen +1

The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks…

cs.CL2023

Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems

Hsuan Su, Rebecca Qian, Chinnadhurai Sankar +4

Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the…

cs.CL20231 cited

Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models

Hsuan Su, Cheng-Chu Cheng, Hua Farn +4

Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots…

cs.CL2023

Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue

Hsuan Su, Shachi H Kumar, Sahisnu Mazumder +7

With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems. The traditional techniques treat knowledge as part of th…

cs.LG2022

Fair Robust Active Learning by Joint Inconsistency

Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen +1

Fairness and robustness play vital roles in trustworthy machine learning. Observing safety-critical needs in various annotation-expensive vision applications, we introduce a novel…

cs.CV20221 cited

Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Hung-Jui Wang, Yu-Yu Wu, Shang-Tse Chen

Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferabil…