Semantically Adversarial Scenario Generation with Explicit Knowledge Guidance
Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional controllable requirements such as embedding a traffic sign in a driving scene by manipulating patterns implicitly in the neuron level. In this paper, we introduce a method to incorporate domain knowledge explicitly in the generation process to achieve the Semantically Adversarial Generation (SAG). To be consistent with the composition of driving scenes, we first categorize the knowledge into two types, the property of objects and the relationship among objects. We then propose a tree-structured variational auto-encoder (T-VAE) to learn hierarchical scene representation. By imposing semantic rules on the properties of nodes and edges in the tree structure, explicit knowledge integration enables controllable generation. We construct a synthetic example to illustrate the controllability and explainability of our method in a succinct setting. We further extend to realistic environments for autonomous vehicles: our method efficiently identifies adversarial driving scenes against different state-of-the-art 3D point cloud segmentation models and satisfies the traffic rules specified as the explicit knowledge.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingAutonomous VehiclesPoint Cloud SegmentationScene GenerationSimilar Papers 제목 키워드 기반
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it of…
knowledge editingAn Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment…
Dialogue GenerationResponse GenerationVocal Bursts Intensity PredictionDANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and v…
Adversarial TextReinforcement LearningRetrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
Non-verbal communication often comprises of semantically rich gestures that help convey the meaning of an utterance. Producing such semantic co-speech gestures has been a major challenge for the existing neural systems t…
Gesture GenerationRAGRetrievalRetrieval-augmented GenerationASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively enca…
Red Teaming