Related papers: Not What You Asked For: Typographic Attacks in Hou…
Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various test-time defense…
A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…
Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with…
Grasping is one of the most fundamental challenging capabilities in robotic manipulation, especially in unstructured, cluttered, and semantically diverse environments. Recent researches have increasingly explored language-guided…
Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling platforms through structured output APIs, but the…
We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddles, code execution) into the model's prompt to indirectly…
While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects. We study…
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…
Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards…
As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…
Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…
Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…
The rise in popularity of text-to-image generative artificial intelligence (AI) has attracted widespread public interest. We demonstrate that this technology can be attacked to generate content that subtly manipulates its users. We propose…
Vision-language-action (VLA) models have shown strong performance in robotic manipulation, yet their robustness to physically realizable adversarial attacks remains underexplored. Existing studies reveal vulnerabilities through language…
Objective no-reference image- and video-quality metrics are crucial in many computer vision tasks. However, state-of-the-art no-reference metrics have become learning-based and are vulnerable to adversarial attacks. The vulnerability of…
This work explores the capacity of large language models (LLMs) to address problems at the intersection of spatial planning and natural language interfaces for navigation. We focus on following complex instructions that are more akin to…
Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming from both environmental and system-level factors. These…
Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability…
Speech and speaker recognition systems are employed in a variety of applications, from personal assistants to telephony surveillance and biometric authentication. The wide deployment of these systems has been made possible by the improved…
Spatial reasoning in large-scale 3D environments such as warehouses remains a significant challenge for vision-language systems due to scene clutter, occlusions, and the need for precise spatial understanding. Existing models often struggle…