Search Results for author:
Found 12 papers, 4 papers with code
CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation
Existing black-box text-based adversarial attacks are ill-suited for evidence-based misinformation detection systems, as these attacks primarily focus on token-level substitutions involving gradient or logit-based optimization strategies, which are incapable of fooling the multi-component nature of these detection systems.
Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal Graphs
Our evaluations demonstrate that training LLMs with SCG Instructions outperforms standard instruction fine-tuning by an average of 35. 69\% on Event Trigger Classification.
Context Matters: An Empirical Study of the Impact of Contextual Information in Temporal Question Answering Systems
Large language models (LLMs) often struggle with temporal reasoning, crucial for tasks like historical event analysis and time-sensitive information retrieval.
AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab
While capstone projects are an excellent example of experiential learning, given the interdisciplinary nature of this emerging social cybersecurity problem, it can be challenging to use them to engage non-computing students without prior knowledge of AI.
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.
Lateral Phishing With Large Language Models: A Large Organization Comparative Study
The emergence of Large Language Models (LLMs) has heightened the threat of phishing emails by enabling the generation of highly targeted, personalized, and automated 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.
