# Searching Realistic-Looking Adversarial Objects For Autonomous Driving Systems

arXiv: https://arxiv.org/abs/2405.11629 · HTML: https://mlsanity.com/paper/2405.11629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 19 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/)

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [AdvHat: Real-world adversarial attack on ArcFace Face ID system](https://mlsanity.com/paper/1908.08705/) (2019)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets](https://mlsanity.com/paper/2308.12067/) (2023)
- [DARTS: Deceiving Autonomous Cars with Toxic Signs](https://mlsanity.com/paper/1802.06430/) (2018)
- [Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4](https://mlsanity.com/paper/2312.16171/) (2023)
- [Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving](https://mlsanity.com/paper/2101.06784/) (2021)
- [On adversarial patches: real-world attack on ArcFace-100 face recognition system](https://mlsanity.com/paper/1910.07067/) (2019)
- [Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization](https://mlsanity.com/paper/2109.06133/) (2021)
- [Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns](https://mlsanity.com/paper/2109.07723/) (2021)
- [MeshAdv: Adversarial Meshes for Visual Recognition](https://mlsanity.com/paper/1810.05206/) (2018)
- [Generating Transferable Adversarial Simulation Scenarios for Self-Driving via Neural Rendering](https://mlsanity.com/paper/2309.15770/) (2023)
- [A short Survey: Exploring knowledge graph-based neural-symbolic system from application perspective](https://mlsanity.com/paper/2405.03524/) (2024)

## Abstract (arXiv)

Numerous studies on adversarial attacks targeting self-driving policies fail to incorporate realistic-looking adversarial objects, limiting real-world applicability. Building upon prior research that facilitated the transition of adversarial objects from simulations to practical applications, this paper discusses a modified gradient-based texture optimization method to discover realistic-looking adversarial objects. While retaining the core architecture and techniques of the prior research, the proposed addition involves an entity termed the 'Judge'. This agent assesses the texture of a rendered object, assigning a probability score reflecting its realism. This score is integrated into the loss function to encourage the NeRF object renderer to concurrently learn realistic and adversarial textures. The paper analyzes four strategies for developing a robust 'Judge': 1) Leveraging cutting-edge vision-language models. 2) Fine-tuning open-sourced vision-language models. 3) Pretraining neurosymbolic systems. 4) Utilizing traditional image processing techniques. Our findings indicate that strategies 1) and 4) yield less reliable outcomes, pointing towards strategies 2) or 3) as more promising directions for future research.