Related papers: SafeVision: Efficient Image Guardrail with Robust …

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…

With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms. Current video guardrails, however, are either overly…

The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can be screened through fast pattern recognition, a small subset…

Image-generative models are widely deployed across industries. Recent studies show that they can be exploited to produce policy-violating content. Existing mitigation strategies primarily operate at the pre- or mid-generation stages through…

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm…

Generative Artificial Intelligence (AI) has created unprecedented opportunities for creative expression, education, and research. Text-to-image systems such as DALL.E, Stable Diffusion, and Midjourney can now convert ideas into visuals…

This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this end, we establish a novel open framework, describing a…

Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to the reproduction of unsafe content such as NSFW imagery and…

With the success of autoregressive learning in large language models, it has become a dominant approach for text-to-image generation, offering high efficiency and visual quality. However, invisible watermarking for visual autoregressive…

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to…

Social media platforms are being increasingly used by malicious actors to share unsafe content, such as images depicting sexual activity, cyberbullying, and self-harm. Consequently, major platforms use artificial intelligence (AI) and human…

Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce…

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

We introduce FAIR-SIGHT, an innovative post-hoc framework designed to ensure fairness in computer vision systems by combining conformal prediction with a dynamic output repair mechanism. Our approach calculates a fairness-aware…

Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing hazard detection systems rely on predefined hazard categories and require intensive…

With rich visual data, such as images, becoming readily associated with items, visually-aware recommendation systems (VARS) have been widely used in different applications. Recent studies have shown that VARS are vulnerable to item-image…

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…

With the advent of text-to-image models and concerns about their misuse, developers are increasingly relying on image safety classifiers to moderate their generated unsafe images. Yet, the performance of current image safety classifiers…

We present an approach towards robust lane tracking for assisted and autonomous driving, particularly under poor visibility. Autonomous detection of lane markers improves road safety, and purely visual tracking is desirable for widespread…