Related papers: Moderating Illicit Online Image Promotion for Unsa…
Recently, ChatGPT, along with DALL-E-2 and Codex,has been gaining significant attention from society. As a result, many individuals have become interested in related resources and are seeking to uncover the background and secrets behind its…
The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to adult and sexually explicit material. Existing detection methods operate on either…
Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…
Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating…
Emerging technologies, particularly artificial intelligence (AI), and more specifically Large Language Models (LLMs) have provided malicious actors with powerful tools for manipulating digital discourse. LLMs have the potential to affect…
Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a subtle yet crucial content-level ethical question is often…
Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges…
The malicious use and widespread dissemination of AI-generated images pose a serious threat to the authenticity of digital content. Existing detection methods exploit low-level artifacts left by common manipulation steps within the…
The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not…
Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically. Motivated by the need to make games replayable, as well as to reduce…
Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, offensive, or culturally inappropriate content when prompted…
Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on…
Recent advances in Multimodal Large Language Models (MLLMs) have introduced a paradigm shift for Image Quality Assessment (IQA) from unexplainable image quality scoring to explainable IQA, demonstrating practical applications like quality…
With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…
Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…
Recent advances in text-to-image diffusion models have enabled the creation of a new form of digital art: optical illusions--visual tricks that create different perceptions of reality. However, adversaries may misuse such techniques to…
This paper investigates the effectiveness of TikTok's enforcement mechanisms for limiting the exposure of harmful content to youth accounts. We collect over 7000 videos, classify them as harmful vs not-harmful, and then simulate…
High Dynamic Range (HDR) videos enhance visual experiences with superior brightness, contrast, and color depth. The surge of User-Generated Content (UGC) on platforms like YouTube and TikTok introduces unique challenges for HDR video…
The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works of AI-generated content detection have been widely studied in the image…
With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…