Related papers: SnapGuard: Lightweight Prompt Injection Detection …

Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, ranging from collaborative problem-solving to autonomous decision-making. However, as these systems become…

The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for…

Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remains underexplored. While agents are vulnerable to visual prompt injections, stealthily executing…

Recently, web-based Large Language Model (LLM) agents autonomously perform increasingly complex tasks, thereby bringing significant convenience. However, they also amplify the risks of malicious misuse cases such as unauthorized collection…

Snapshot testing has emerged as a critical technique for UI validation in modern software development, yet it suffers from substantial maintenance overhead due to frequent UI changes causing test failures that require manual inspection to…

The task of medical image recognition is notably complicated by the presence of varied and multiple pathological indications, presenting a unique challenge in multi-label classification with unseen labels. This complexity underlines the…

Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect latent intent beyond keywords, making token-level…

The widespread use of clickbait headlines, crafted to mislead and maximize engagement, poses a significant challenge to online credibility. These headlines employ sensationalism, misleading claims, and vague language, underscoring the need…

The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current…

Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and…

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…

With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage in multi-turn interactions during image refinement: a…

Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they…

Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data. These systematic errors…

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…

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…