Search Results for author:
Found 4 papers, 0 papers with code
Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent
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.
The Application of Differential Privacy for Rank Aggregation: Privacy and Accuracy
The potential risk of privacy leakage prevents users from sharing their honest opinions on social platforms.
Wisdom of the Crowd: Incorporating Social Influence in Recommendation Models
In this paper, we propose two recommendation models, for individuals and for groups respectively, based on social contagion and social influence network theory.
A Random Walk Based Model Incorporating Social Information for Recommendations
Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system.
