Yang Zhang

Yang Zhang

Auto-generated profile, based on publicly available information

Yang Zhang

Miami University, Miami, Florida, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
7 November 2022
Verified
Conference Paper
Open access
WSWai Man Si
Wai Man Si
MBMichael Backes
Michael Backes
JBJeremy Blackburn
Jeremy Blackburn
ECEmiliano De Cristofaro
Emiliano De Cristofaro
GSGianluca Stringhini
Gianluca Stringhini
YZYang Zhang
Yang Zhang
Chatbots are used in many applications, e.g., automated agents, smart home assistants, interactive characters in online games, etc. Therefore, it is crucial to ensure they do not behave in undesired manners, providing offensive or toxic responses to users. This is not a trivial task as state-of-the-art chatbot models are trained on large, public datasets openly collected from the Internet. This paper presents a first-of-its-kind, large-scale measurement of toxicity in chatbots. We show that publicly available chatbots are prone to providing toxic responses when fed toxic queries. Even more worryingly, some non-toxic queries can trigger toxic responses too. We then set out to design and experiment with an attack, ToxicBuddy, which relies on fine-tuning GPT-2 to generate non-toxic queries that make chatbots respond in a toxic manner. Our extensive experimental evaluation demonstrates that our attack is effective against public chatbot models and outperforms manually-crafted malicious queries proposed by previous work. We also evaluate three defense mechanisms against ToxicBuddy, showing that they either reduce the attack performance at the cost of affecting the chatbot's utility or are only effective at mitigating a portion of the attack. This highlights the need for more research from the computer security and online safety communities to ensure that chatbot models do not hurt their users. Overall, we are confident that ToxicBuddy can be used as an auditing tool and that our work will pave the way toward designing more effective defenses for chatbot safety.

10 April 2018 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
DZDaniel Zhang
Daniel Zhang
DWDong Wang
Dong Wang
NVNathan Vance
Nathan Vance
YZYang Zhang
Yang Zhang
SMSteven Mike
Steven Mike
Identifying trustworthy information in the presence of noisy data contributed by numerous unvetted sources from online social media (e.g., Twitter, Facebook, and Instagram) has been a crucial task in the era of big data. This task, referred to as truth discovery, targets at identifying the reliability of the sources and the truthfulness of claims they make without knowing either a priori. In this work, we identified three important challenges that have not been well addressed in the current truth discovery literature. The first one is "misinformation spread" where a significant number of sources are contributing to false claims, making the identification of truthful claims difficult. For example, on Twitter, rumors, scams, and influence bots are common examples of sources colluding, either intentionally or unintentionally, to spread misinformation and obscure the truth. The second challenge is "data sparsity" or the "long-tail phenomenon" where a majority of sources only contribute a small number of claims, providing insufficient evidence to determine those sources' trustworthiness. For example, in the Twitter datasets that we collected during real-world events, more than 90% of sources only contributed to a single claim. Third, many current solutions are not scalable to large-scale social sensing events because of the centralized nature of their truth discovery algorithms. In this paper, we develop a Scalable and Robust Truth Discovery (SRTD) scheme to address the above three challenges. In particular, the SRTD scheme jointly quantifies both the reliability of sources and the credibility of claims using a principled approach. We further develop a distributed framework to implement the proposed truth discovery scheme using Work Queue in an HTCondor system. The evaluation results on three real-world datasets show that the SRTD scheme significantly outperforms the state-of-the-art truth discovery methods in terms of both effectiveness and efficiency.

22 April 2025
Verified
Conference Paper
Open access
YLYifan Liu
Yifan Liu
YLYaokun Liu
Yaokun Liu
ZLZelin Li
Zelin Li
RYRuichen Yao
Ruichen Yao
YZYang Zhang
Yang Zhang
DWDong Wang
Dong Wang

1 January 2024
Verified
Conference Paper
Open access
PDF file
ZYZhenrui Yue
Zhenrui Yue
HZHuimin Zeng
Huimin Zeng
YLYimeng Lu
Yimeng Lu
LSLanyu Shang
Lanyu Shang
YZYang Zhang
Yang Zhang
DWDong Wang
Dong Wang
Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, Dong 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.

1 January 2024
Verified
Conference Paper
Open access
PDF file
ZYZhenrui Yue
Zhenrui Yue
HZHuimin Zeng
Huimin Zeng
LSLanyu Shang
Lanyu Shang
YLYifan Liu
Yifan Liu
YZYang Zhang
Yang Zhang
DWDong Wang
Dong Wang
Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, Dong Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 September 2020 in Social Network Analysis and Mining
Verified
Journal Article
Closed access
PDF file
LSLanyu Shang
Lanyu Shang
YZYang Zhang
Yang Zhang
DZDaniel Zhang
Daniel Zhang
DWDong Wang
Dong Wang