no code implementations • 6 May 2024 • Shang Shang, Xinqiang Zhao, Zhongjiang Yao, Yepeng Yao, Liya Su, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang
To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by obfuscating the true intentions behind user prompts. This approach compels LLMs to inadvertently generate restricted content, bypassing their built-in content security measures.
no code implementations • 24 Sep 2014 • Shang Shang, Tiance Wang, Paul Cuff, Sanjeev Kulkarni
The potential risk of privacy leakage prevents users from sharing their honest opinions on social platforms.
no code implementations • 3 Aug 2012 • Shang Shang, Pan Hui, Sanjeev R. Kulkarni, Paul W. Cuff
In this paper, we propose two recommendation models, for individuals and for groups respectively, based on social contagion and social influence network theory.
no code implementations • 3 Aug 2012 • Shang Shang, Sanjeev R. Kulkarni, Paul W. Cuff, Pan Hui
Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system.