paper-with-me

Papers

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks

2024-03-04 · Zijian Huang, Wenda Chu, Linyi Li, Chejian Xu, Bo Li

Multi-sensor fusion systems (MSFs) play a vital role as the perception module in modern autonomous vehicles (AVs). Therefore, ensuring their robustness against common and realistic adversarial semantic transformations, such as rotation and shifting in the physical world, is crucial for the safety of AVs. While empirical evidence suggests that MSFs exhibit improved robustness compared to single-modal models, they are still vulnerable to adversarial semantic transformations. Despite the proposal of empirical defenses, several works show that these defenses can be attacked again by new adaptive attacks. So far, there is no certified defense proposed for MSFs. In this work, we propose the first robustness certification framework COMMIT certify robustness of multi-sensor fusion systems against semantic attacks. In particular, we propose a practical anisotropic noise mechanism that leverages randomized smoothing with multi-modal data and performs a grid-based splitting method to characterize complex semantic transformations. We also propose efficient algorithms to compute the certification in terms of object detection accuracy and IoU for large-scale MSF models. Empirically, we evaluate the efficacy of COMMIT in different settings and provide a comprehensive benchmark of certified robustness for different MSF models using the CARLA simulation platform. We show that the certification for MSF models is at most 48.39% higher than that of single-modal models, which validates the advantages of MSF models. We believe our certification framework and benchmark will contribute an important step towards certifiably robust AVs in practice.

📄 PDF Abstract BibTeX arXiv:2403.02329

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehiclesobject-detectionObject DetectionSensor Fusion

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
CARLA CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban…
Randomized Smoothing 설명 없음

Similar Papers 제목 키워드 기반

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion

2025-07-10 · Frederick Shpilevskiy, Saiyue Lyu, Krishnamurthy Dj Dvijotham, Mathias Lécuyer 외 arxiv

We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insight is to reinterpret a guided denoising …

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

2025-02-09 · Bowei He, Lihao Yin, Hui-Ling Zhen, Jianping Zhang 외

The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliabi…

Language ModelingLanguage Modelling

Trustless Audits without Revealing Data or Models

2024-04-06 · Suppakit Waiwitlikhit, Ion Stoica, Yi Sun, Tatsunori Hashimoto 외

There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholder wishing to know whether their copyrigh…

counterfactualimage-classificationImage ClassificationRecommendation Systems

Incremental Randomized Smoothing Certification

2023-05-31 · Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh 외

Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifie…

Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness

2024-05-25 · Jieren Deng, Hanbin Hong, Aaron Palmer, Xin Zhou 외

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data au…

Adversarial RobustnessData Augmentation