Publications

2027

User Perceptions of Deceptive In-Vehicle Infotainment User Interfaces
Pedram MohajerAnsari, Iwinosa Aideyan, Anna Galeano, Arjun Arunasalam, Bart Knijnenburg, Richard Brooks, Mert D. Pesé.
NDSS 2027

Meta-VLM: Which Metadata Do Vision-Language Models Need to Drive Safely?
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé.
WACV 2027

2026

Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation
Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé.
NeurIPS 2026

On the Vulnerability of Lane Detectors to Physical Shadow Attack
Pedram MohajerAnsari, Amir Salarpour, Jan de Voor, Arkajyoti Mitra, Alkim Domeke, Habeeb Olufowobi, Mohammad Hamad, Mert D. Pesé.
ACSAC 2026

GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models
Pedram MohajerAnsari*, Amir Salarpour*, Run Wang, Mert D. Pesé.
BMVC 2026

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles
Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé.
IROS 2026

SoK: Security of the Image Processing Pipeline in Autonomous Vehicles
Michael Kühr, Mohammad Hamad, Pedram MohajerAnsari, Mert D. Pesé, Sebastian Steinhorst.
AsiaCCS 2026

Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection
Pedram MohajerAnsari, Amir Salarpour, David Fernandez, Mert D. Pesé.
IEEE ICIP 2026

From MIRAGE to CLEAR: Component-Level Explainable Anomaly Reasoning for Autonomous Vehicle Perception Systems
David Fernandez, Pedram MohajerAnsari, Cigdem Kokenoz, Amir Salarpour, Bing Li, Mert D. Pesé.
DSN 2026

Interpretable Adversarial Prompt Tuning via Semantic Concepts
Pedram MohajerAnsari, Zongxi Liu, Yi Zhu, Amir Salarpour, Mert D. Pesé.
CVPR-AdvML 2026

SASA: Sequence-Aware Shadow Attacks via Attention Alignment for Traffic Sign Recognition
Amir Salarpour*, Pedram MohajerAnsari*, David Fernandez, Mert D. Pesé.
CVPR-AdvML 2026

Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?
Ashton B. McEntarffer, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé.
CVPR-AdvML 2026

SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé.
ICRA 2026

NPNet: A Non-Parametric Network with Adaptive Gaussian–Fourier Positional Encoding for 3D Classification and Segmentation
Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé.
IEEE IV 2026

Toward Inherently Robust VLMs Against Visual Perception Attacks
Pedram MohajerAnsari, Amir Salarpour, Michael Kühr, Siyu Huang, Mohammad Hamad, Habeeb Olufowobi, Sebastian Steinhorst, Bing Li, Mert D. Pesé.
IEEE IV 2026

Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé.
SAE Technical Paper 2026

Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Long Cheng, Abolfazl Razi, Mert D. Pesé.
IEEE IV 2026

2025

Attention-Aware Temporal Adversarial Shadows on Traffic Sign Sequences
Pedram MohajerAnsari, Amir Salarpour, David Fernandez, Cigdem Kokenoz, Bing Li, Mert D. Pesé.
CVPR-AdvML 2025

Forensic Reconstruction of Traffic Incidents: A Vision-Language Model Framework for Post-Incident Forensic Analysis
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Cigdem Kokenoz, Bing Li, Richard Brooks, Mert D. Pesé.
IEEE MultiMedia 2025

Avoiding the Crash: A Vision-Language Model Evaluation of Critical Traffic Scenarios
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé.
SAE Technical Paper 2025 · Best Paper

Beyond the Glow: Understanding Luminescent Marker Behavior Against AV Perception Systems
Arkajyoti Mitra, Pedram MohajerAnsari, Afia Anjum, Paul Agbaje, Mert D. Pesé, Habeeb Olufowobi.
VehicleSec 2025

WIP: From Detection to Explanation: Using LLMs for Adversarial Scenario Analysis in Vehicles
David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Cigdem Kokenoz, Bing Li, Mert D. Pesé.
VehicleSec 2025

Point-LN: A Lightweight Framework for Efficient Point Cloud Classification Using Non-Parametric Positional Encoding
Marzieh Mohammadi, Amir Salarpour, Pedram MohajerAnsari.
CSICC 2025

Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari.
IPRIA 2025

2024

WIP: A First Look At Employing Large Multimodal Models Against Autonomous Vehicle Attacks
Mohammed Aldeen*, Pedram MohajerAnsari*, Jin Ma, Mashrur Chowdhury, Long Cheng, Mert D. Pesé.
VehicleSec 2024

An Initial Exploration of Employing Large Multimodal Models in Defending Against Autonomous Vehicles Attacks
Mohammed Aldeen*, Pedram MohajerAnsari*, Jin Ma, Mashrur Chowdhury, Long Cheng, Mert D. Pesé.
IEEE IV 2024

Achieving the Safety and Security of the End-to-End AV Pipeline
Noah T. Curran, Minkyoung Cho, Ryan Feng, Liangkai Liu, Brian Jay Tang, Pedram MohajerAnsari, Alkim Domeke, Mert D. Pesé, Kang G. Shin.
CSCS 2024

Transforming In-Vehicle Network Intrusion Detection: VAE-based Knowledge Distillation Meets Explainable AI
Muhammet Anil Yagiz, Pedram MohajerAnsari, Mert D. Pesé, Polat Goktas.
CPSIoT-Sec 2024