Search Results for author:
Found 16 papers, 2 papers with code
Interior-Point Vanishing Problem in Semidefinite Relaxations for Neural Network Verification
Semidefinite programming (SDP) relaxation has emerged as a promising approach for neural network verification, offering tighter bounds than other convex relaxation methods for deep neural networks (DNNs) with ReLU activations.
Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks.
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
Specifically, we propose three distinct attack mechanisms: word injection, scenario manipulation, and knowledge injection, targeting various components in the LLM-based decision-making pipeline.
Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception
We evaluate the effectiveness of the ILR attack with real-world experiments against two major traffic sign recognition architectures on four IR-sensitive cameras.
Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
The NDD attack shows a significantly high capability to generate low-cost, model-agnostic, and transferable adversarial attacks by exploiting the natural attack capability in diffusion models.
Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
In this work, we conduct the first measurement study on whether and how effectively the existing designs can lead to system-level effects, especially for the STOP sign-evasion attacks due to their popularity and severity.
LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies
To fill these critical research gaps, we conduct the first large-scale measurement study on LiDAR spoofing attack capabilities on object detectors with 9 popular LiDARs, covering both first- and new-generation LiDARs, and 3 major types of object detectors trained on 5 different datasets.
Learning Representation for Anomaly Detection of Vehicle Trajectories
We conduct extensive experiments to demonstrate that our supervised method based on contrastive learning and unsupervised method based on reconstruction with semantic latent space can significantly improve the performance of anomalous trajectory detection in their corresponding settings over various baseline methods.
Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction
In this paper, we present a novel adversarial training method for trajectory prediction.
Semi-supervised Semantics-guided Adversarial Training for Trajectory Prediction
In addition, experiments show that our method can significantly improve the system's robust generalization to unseen patterns of attacks.
Towards Driving-Oriented Metric for Lane Detection Models
After the 2017 TuSimple Lane Detection Challenge, its dataset and evaluation based on accuracy and F1 score have become the de facto standard to measure the performance of lane detection methods.
SoK: On the Semantic AI Security in Autonomous Driving
In this paper, we perform the first systematization of knowledge of such growing semantic AD AI security research space.
On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
We demonstrate that the conventional evaluation fails to reflect the robustness in end-to-end autonomous driving scenarios.
End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering
The experiment results demonstrate that our approach can effectively mitigate the impact of adversarial attacks and can achieve 55% to 90% improvement over the original OpenPilot.
Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attack
Automated Lane Centering (ALC) systems are convenient and widely deployed today, but also highly security and safety critical.
Security of Deep Learning based Lane Keeping System under Physical-World Adversarial Attack
Lane-Keeping Assistance System (LKAS) is convenient and widely available today, but also extremely security and safety critical.
