Search Results for author:
Found 8 papers, 4 papers with code
Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models
Online user-generated content games (UGCGs) are increasingly popular among children and adolescents for social interaction and more creative online entertainment.
Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
This process involves addressing two key problems: (1) the reason for obfuscating unsafe images demands the platform to provide an accurate rationale that must be grounded in unsafe image-specific attributes, and (2) the unsafe regions in the image must be minimally obfuscated while still depicting the safe regions.
Large Language Model Lateral Spear Phishing: A Comparative Study in Large-Scale Organizational Settings
The critical threat of phishing emails has been further exacerbated by the potential of LLMs to generate highly targeted, personalized, and automated spear phishing attacks.
Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text
We first study the effectiveness of state-of-the-art approaches and find that they are severely limited against text produced by diverse generators and domains in the real world.
An Investigation of Large Language Models for Real-World Hate Speech Detection
Our study reveals that a meticulously crafted reasoning prompt can effectively capture the context of hate speech by fully utilizing the knowledge base in LLMs, significantly outperforming existing techniques.
Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models
HATEGUARD further achieves prompt-based zero-shot detection by automatically generating and updating detection prompts with new derogatory terms and targets in new wave samples to effectively address new waves of online hate.
Understanding and Measuring Robustness of Multimodal Learning
We then introduce a new type of multimodal adversarial attacks called decoupling attack in MUROAN that aims to compromise multimodal models by decoupling their fused modalities.
CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks.
