VehicleSec '26
2026-08-10..2026-08-11
Baltimore, United States
who it's for
automotive security engineers, embedded firmware engineers, intrusion detection researchers, connected vehicle architects, ev charging and infrastructure security engineers, security auditors and regulators, vehicle penetration testers
topics
CAN bus intrusion detection; firmware debloating for vehicles; secure OTA update techniques; V2X spoofing and EEBL detection; LiDAR sensor vulnerability analysis; camera latency and perception attacks; physical-layer vehicle fingerprinting; ISO/SAE 21434 risk assessment; ISO 15118 relay charging attacks; MQTT-SN gateway fuzzing; human-in-the-loop intrusion response; vehicle firmware reverse engineering
| title | author | length |
|---|---|---|
| The Trajectory of Automotive Cybersecurity and the Role of AI | André Weimerskirch | 41m |
Automotive security shifts from hype to regulation: ISO SAE 21434 and type‑approval rules force heavy compliance, where risk assessment takes 2–4 weeks per… | ||
| Blind Spot in Sensor Fusion: Exploiting an Architectural Vulnerability to Hijack... | Jongsoo Han, Seulbae Kim | 13m |
Shows that PX4 and ArduPilot’s architecture leaves a persistent blind spot: injected gyroscope bias immediately alters control outputs while GPS-based fusion… | ||
| SHIELD: Secure Human-Machine Interaction with Evidential Learning and Dynamic... | Dawood Wasif, Terrence J. Moore, Seunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Frederica F. Nelson, Jin-Hee Cho | 14m |
SHIELD is a decentralized swarm-control framework that uses evidential vacuity (Dirichlet-based perception) to drive a dynamic trust graph and an embedded… | ||
| SLEIGHT: Real-time Closed-Loop Attack Analytics Framework for Holistic Intrusion... | Muneeba Asif, Maryna Veksler, Devrim Aras, Kemal Akkaya, Mohammad Ashiqur Rahman | 20m |
SLEIGHT is a real-time attack analytics framework that trains a conditional GAN with a phase-conditioned RL policy (PPO) plus an attacker-side plausibility… | ||
| E-Trojans: Ransomware, Tracking, DoS, and Data Leaks on the Xiaomi E-Scooter... | Marco Casagrande, Riccardo Cestaro, Mauro Conti, Eleonora Losiouk, Daniele Antonioli | 18m |
Reverse-engineering of Xiaomi M365 and Mi3 internals uncovers four flaws that enable arbitrary code execution on the BMS and unsigned, unencrypted firmware… | ||
| RVDebloater: Mode-based Adaptive Firmware Debloating for Robotic Vehicles | Mohsen Salehi, Karthik Pattabiraman | 14m |
RVDebloater claims mode-based, reversible firmware debloating that identifies per-mode needed functions with static and dynamic analysis, instruments indirect… | ||
| CANBERT+: An Optimized Multi-Layer BERT-Based Intrusion Detection for CAN Bus | Jun Yeon Won, Qadeer Ahmed, Zhiqiang Lin | 14m |
A BERT-derived IDS represents each CAN message as a single token with multi-layer embeddings for ID, length and payload bytes, reducing sequence length so… | ||
| MIRAGE: Detecting Fake Emergency Electronic Brake Light Attacks in V2X Networks... | Eunhan Ka, Doguhan Yeke, Z. Berkay Celik, Satish Ukkusuri | 17m |
MIRAGE is an event-gated detector that activates only on EEBL flags, computes position-derived speed to catch discrepancies and detects post-attack… | ||
| On the Real-World Applicability of Automotive CAN Intrusion Detection Systems | Kristijan Lazeski, Michael Zohner, Jannis Hamborg, Christoph Krauß, Alexander Wiesmaier | 12m |
Analyzes five widely used CAN datasets, trains interpretable decision trees, and tests against an on-bus attacker that can observe, inject, replay, spoof, and… | ||
| CARdea: Two-Phase Plausibility-Based Vehicle-to-Vehicle Anomaly Detection... | Mert D. Pesé, Arman Tabaddor, Teja Guruvelli, Roland Varriale, Marco De Vincenzi, Kang G. Shin | 12m |
A practical V2V anomaly detector called CARdea implements a two-phase pipeline: a lightweight in-vehicle statistical stage that flags anomalies with up to 98%… | ||
| SNFuzz: Gateway-Centric State-Oriented Fuzzing for MQTT-SN | Christian de la Pena, Samin Y. Chowdhury, Mohammad Ashiqur Rahman, Weidong Zhu, Ruimin Sun | 10m |
SNFuzz models gateway-managed MQTT-SN state and drives inputs by gateway responses, using a state manager that issues mutated UDP packets (injection, deletion… | ||
| Digital Eyes on the Road: Using Street Cameras to Verify Traffic Integrity and... | Jhonatan Tavori, Mehmet Kerem Turkcan, Zoran Kostic, Salvatore Stolfo, Gil Zussman | 17m |
An end-to-end pipeline links NYC DOT street cameras (200+ in Manhattan) to TomTom road-level telemetry, uses low-resolution YOLO-based object counts, aligns… | ||
| Charge It to My Neighbor: A Relay Attack on ISO 15118 Plug and Charge Payment | Jakob Löw, Vishwa Vasu, Thomas Hutzelmann, Hans-Joachim Hof | 14m |
A relay attack on ISO 15118 plug-and-charge is demonstrated end-to-end: a proof-of-concept forks an open-source ISO 15118 stack and runs on real hardware with… | ||
| Race to Charge: Concurrency Bugs and State Integrity Violations in EV... | Jaeyeong Lee, Seonhyeong Lee | 09m |
Manual audit and sanitizer-assisted experiments on Everest Core version 2025.12.1 uncover 11 concurrency vulnerabilities now issued as 11 CVEs, including eight… | ||
| Research Only? Understanding the Scope of Automotive... | Stefan Savage | 44m |
Research shows stock cars can be remotely taken over—engine, brakes and steering controlled in demos—and getting from PoC to reliable exploit is expensive… | ||
| When Collaboration Betrays: The Evolving Attack Surface of... | Qingzhao Zhang | 06m |
Claims that a malicious collaborator can craft shared feature maps to produce 0.5 m post-perturbation of an object’s reported position and, in CARLA scenarios… | ||
| The Law Bites Before the Code Does: Designing Vehicle... | Joseph Squillace | 06m |
Predictive maintenance is technically solved but legally messy: design must answer three design questions before training — what data may be collected and how… | ||
| Toward Physical-Layer Fingerprinting of Production Automotive... | Abbas Ali, Hafiz Malik | 04m |
Claims physical-layer CAN fingerprints separate identical units by manufacturing variation, validated on bench dev boards and on nine identical production ECUs… | ||
| A Study on Extending the TARA Methodology for Physical AI: A Case Study of ADS | Jihun Woo, Junhyeong Lee | 15m |
Extends STRIDE by merging MITRE ATLAS and OWASP Top 10 for LLMs into a unified TARA that normalizes 170 sources into 89 attack scenarios and generates 595… | ||
| AutoHack: A Physically Verified Multi-Bus CAN Dataset for Intrusion Detection... | Yuchan Song, Sejun Ahn, Seungjin Baek, Hyeonseong Kim, Huy Kang Kim, Sanghoon Jeon | 14m |
A 2023 Hyundai–based dataset captures synchronized C-CAN P-CAN B-CAN traffic with a dual‑channel CAN logger and a single timestamp base, totaling 9.6 billion… | ||
| Bridging Two TARAs: Integrating MITRE CTSA/CRRA Prioritization into ISO/SAE... | Minhyuk Park, Yejun Kim, Seungjoo Kim | 12m |
AutoTARA automates ISO/SAE 21434 TARA by combining Meta Attack Language (MAL) system models and VehicleLang simulation with MITRE TARA-style CTSA/CRRA… | ||
| Perspective-Shift Attacks Against Optical Perception Sensors: A Novel Attack... | Marco Calipari, Michael Kühr, Dominik Kulmer, Maximilian Luedecke, Mohammad Hamad, Sebastian Steinhorst | 16m |
Paper demonstrates that placing a transparent Direction Turning Film over LiDAR and camera optics produces a controlled 20° shift in field of view, causing… | ||
| Seeing is Deceiving: Systematic Vulnerability Analysis of LiDAR-Based Autonomous... | Selma Yahia, Ildi Alla, Girija B. Mohan, Daniel Rau, Mridula Singh, Valeria Loscri | 14m |
Systematic tests show planar mirrors cause two reproducible failures: Object Addition (phantom obstacles) and Object Removal (real obstacles vanish)… | ||
| Investigating Stealthy Latency Attacks Against Camera-Based Object... | Lichen Xia, Xing Gao, Weisong Shi | 10m |
Groundswell crafts a single universal sticker/projection perturbation using Regional Perturbation Balance and PGD to inject phantom proposals into camera… | ||
| Beyond Classical PKI: A Quantum-Safe Authentication Framework for Automotive OTA... | Wei-Lun Lin, Ting-Yu Chen, Arijit Karati | 15m |
Proposes a deployable quantum-safe OTA authentication protocol that uses Leighton-Micali Signatures for server identity and Module-Lattice ML-KEM to derive… | ||
| VIN2VICTIM: From Vehicle Identification to Targeted Tracking via Data... | Hannaneh B. Pasandi, Mohammad Sepahi | 18m |
VIN2VICTIM converts a single VIN into targeted physical tracking through four stages: owner deanonymization, trajectory reidentification, home/work inference… | ||
| Is Your ECU Really Yours? | Abbas Ali, Hafiz Malik | 11m |
Claims a physical fingerprinting system that distinguishes identical ECUs by capturing analog switching transients with a Red Pitaya data acquisition board and… | ||
| RAIL: Risk-Aware Human-in-the-Loop Framework with Adaptive Intrusion Response... | Dawood Wasif, Terrence J. Moore, Seunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Frederica F. Nelson, Jin-Hee Cho | 15m |
RAIL is a runtime framework that fuses heterogeneous cues into an Intrusion Risk Index (IRI) using a weighted Noisy‑OR over curvature actuation integrity… | ||
| Reversing a Brake ECU Firmware Update | Ben Gardiner | 18m |
Reverse engineering of the ID9363 updater extracts firmware from three EC80 Brake ECUs using the S12X background debug module and IDA Pro, then automates… | ||
| Patchlings: Enabling A/B-Equivalent OTA Updates for Deeply Embedded... | Sekar Kulandaivel | 16m |
Patchlings preserves the original firmware untouched, instruments function entry points with static trampolines, and redirects bounded control flow into a… | ||
| Constructive Assurance Cases for Cybersecurity | Anuja Sonalker | 31m |
Argues a concrete method: start assurance cases at project start, use eliminative argumentation to turn TAR outputs into top-level claims, then drive… | ||
| CAUTION: HIGH VOLTAGE, LOW SECURITY – A Familiar Tale of... | Maggie Shipman | 16m |
Demonstrates an ISO 15118‑2 SLAC vulnerability where a lab-built man‑in‑the‑middle via self‑reported signal forces pairing between car and charger, reads full… | ||
| nothing matches | ||