Search papers, labs, and topics across Lattice.
The paper introduces a novel method, AUTHENTICATION, to identify rare failure modes (RFMs) in autonomous vehicle perception systems by leveraging adversarially guided diffusion models. It uses segmentation masks of objects, inverts them to create environmental masks, and combines these with text prompts to guide a Stable Diffusion inpainting model, optimized with adversarial noise, to generate images that expose vulnerabilities in object detection models. The generated RFMs are then described using natural language to aid developers in improving AV safety and reliability.
Uncover hidden vulnerabilities in autonomous vehicle perception by generating realistic, adversarial failure scenarios with diffusion models, revealing the long-tail challenges that plague even well-trained systems.
Autonomous Vehicles (AVs) rely on artificial intelligence (AI) to accurately detect objects and interpret their surroundings. However, even when trained using millions of miles of real-world data, AVs are often unable to detect rare failure modes (RFMs). The problem of RFMs is commonly referred to as the"long-tail challenge", due to the distribution of data including many instances that are very rarely seen. In this paper, we present a novel approach that utilizes advanced generative and explainable AI techniques to aid in understanding RFMs. Our methods can be used to enhance the robustness and reliability of AVs when combined with both downstream model training and testing. We extract segmentation masks for objects of interest (e.g., cars) and invert them to create environmental masks. These masks, combined with carefully crafted text prompts, are fed into a custom diffusion model. We leverage the Stable Diffusion inpainting model guided by adversarial noise optimization to generate images containing diverse environments designed to evade object detection models and expose vulnerabilities in AI systems. Finally, we produce natural language descriptions of the generated RFMs that can guide developers and policymakers to improve the safety and reliability of AV systems.
