Wenjie Wang

According to our database, Wenjie Wang authored at least 18 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures.

Yukai Zhou, Sibei Yang, Wenjie Wang

CoRR, June, 2025

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning.

Hongye Qiu, Yue Xu, Meikang Qiu, Wenjie Wang

CoRR, February, 2025

Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models.

Yue Xu, Chengyan Fu, Li Xiong, Sibei Yang, Wenjie Wang

CoRR, February, 2025

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training.

Fenghua Weng, Jian Lou, Jun Feng, Minlie Huang, Wenjie Wang

CoRR, February, 2025

Don't Say No: Jailbreaking LLM by Suppressing Refusal.

Yukai Zhou, Jian Lou, Zhijie Huang, Zhan Qin, Sibei Yang, Wenjie Wang

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

<i>MMJ-Bench</i>: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models.

Fenghua Weng, Yue Xu, Chengyan Fu, Wenjie Wang

CoRR, 2024

Defending Jailbreak Attack in VLMs via Cross-modality Information Detector.

Yue Xu, Xiuyuan Qi, Zhan Qin, Wenjie Wang

CoRR, 2024

Don't Say No: Jailbreaking LLM by Suppressing Refusal.

Yukai Zhou, Wenjie Wang

CoRR, 2024

Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing.

Chengyan Fu, Wenjie Wang

CoRR, 2024

LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models.

Yue Xu, Wenjie Wang

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.

Yue Xu, Xiuyuan Qi, Zhan Qin, Wenjie Wang

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

IGAMT: Privacy-Preserving Electronic Health Record Synthesization with Heterogeneity and Irregularity.

Wenjie Wang, Pengfei Tang, Jian Lou, Yuanming Shao, Lance Waller, Yi-an Ko, Li Xiong

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Wasserstein Adversarial Examples on Univariant Time Series Data.

Wenjie Wang, Li Xiong, Jian Lou

CoRR, 2023

Demo: Certified Robustness on Toolformer.

Yue Xu, Wenjie Wang

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

2022

Generating Adversarial Examples With Distance Constrained Adversarial Imitation Networks.

Pengfei Tang, Wenjie Wang, Jian Lou, Li Xiong

IEEE Trans. Dependable Secur. Comput., 2022

2021

Certified Robustness to Word Substitution Attack with Differential Privacy.

Wenjie Wang, Pengfei Tang, Jian Lou, Li Xiong

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

2020

RADAR: Recurrent Autoencoder Based Detector for Adversarial Examples on Temporal EHR.

Wenjie Wang, Pengfei Tang, Li Xiong, Xiaoqian Jiang

Proceedings of the Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track, 2020

Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries.

Wenjie Wang, Youngja Park, Taesung Lee, Ian M. Molloy, Pengfei Tang, Li Xiong

Proceedings of the 3rd Clinical Natural Language Processing Workshop, 2020