Lu Lin

Lu Lin

Auto-generated profile, based on publicly available information

Lu Lin

College of Information Sciences and Technology Pennsylvania State University University 16802 Park PA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
BCBochuan Cao
Bochuan Cao
YCYuanpu Cao
Yuanpu Cao
LLLu Lin
Lu Lin
JCJinghui Chen
Jinghui Chen
Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 January 2024
Verified
Conference Paper
Open access
PDF file
HZHangfan Zhang
Hangfan Zhang
ZGZhimeng Guo
Zhimeng Guo
HZHuaisheng Zhu
Huaisheng Zhu
BCBochuan Cao
Bochuan Cao
LLLu Lin
Lu Lin
DWDinghao Wu
Dinghao Wu
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, Dinghao Wu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 January 2025
Verified
Conference Paper
Open access
PDF file
YCYurui Chang
Yurui Chang
BCBochuan Cao
Bochuan Cao
YWYujia Wang
Yujia Wang
JCJinghui Chen
Jinghui Chen
LLLu Lin
Lu Lin
Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

1 January 2025
Verified
Conference Paper
Open access
PDF file
YCYurui Chang
Yurui Chang
BCBochuan Cao
Bochuan Cao
LLLu Lin
Lu Lin
Yurui Chang, Bochuan Cao, Lu Lin. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

9 August 2024 in arXiv
Verified
Preprint
Open access
PDF file
YCYuanpu Cao
Yuanpu Cao
LLLu Lin
Lu Lin
JCJinghui Chen
Jinghui Chen
Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not be satisfactory due to the existence of adversarial examples, which pose significant threats to the practical deployment of deep anomaly detectors. Recently, it has been shown that diffusion models can be used to purify the adversarial noises and thus build a robust classifier against adversarial attacks. Unfortunately, we found that naively applying this strategy in anomaly detection (i.e., placing a purifier before an anomaly detector) will suffer from a high anomaly miss rate since the purifying process can easily remove both the anomaly signal and the adversarial perturbations, causing the later anomaly detector failed to detect anomalies. To tackle this issue, we explore the possibility of performing anomaly detection and adversarial purification simultaneously. We propose a simple yet effective adversarially robust anomaly detection method, \textit{AdvRAD}, that allows the diffusion model to act both as an anomaly detector and adversarial purifier. We also extend our proposed method for certified robustness to $l_2$ norm bounded perturbations. Through extensive experiments, we show that our proposed method exhibits outstanding (certified) adversarial robustness while also maintaining equally strong anomaly detection performance on par with the state-of-the-art methods on industrial anomaly detection benchmark datasets.

2 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
HZHangfan Zhang
Hangfan Zhang
ZGZhimeng Guo
Zhimeng Guo
HZHuaisheng Zhu
Huaisheng Zhu
BCBochuan Cao
Bochuan Cao
LLLu Lin
Lu Lin
DWDinghao Wu
Dinghao Wu
Large Language Models (LLMs) have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misused to generate undesired content. In response, before releasing LLMs for public access, model developers usually align those language models through Supervised Fine-Tuning (SFT) or Reinforcement Learning with Human Feedback (RLHF). Consequently, those aligned large language models refuse to generate undesired content when facing potentially harmful/unethical requests. A natural question is "could alignment really prevent those open-sourced large language models from being misused to generate undesired content?''. In this work, we provide a negative answer to this question. In particular, we show those open-sourced, aligned large language models could be easily misguided to generate undesired content without heavy computations or careful prompt designs. Our key idea is to directly manipulate the generation process of open-sourced LLMs to misguide it to generate undesired content including harmful or biased information and even private data. We evaluate our method on 4 open-sourced LLMs accessible publicly and our finding highlights the need for more advanced mitigation strategies for open-sourced LLMs.