# SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving

arXiv: https://arxiv.org/abs/2604.01337 · HTML: https://mlsanity.com/paper/2604.01337/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)
- [Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB](https://mlsanity.com/paper/1804.02675/) (2018)
- [DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation](https://mlsanity.com/paper/2107.10189/) (2021)
- [A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents](https://mlsanity.com/paper/2106.10197/) (2021)
- [Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization](https://mlsanity.com/paper/1705.06560/) (2017)
- [GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models](https://mlsanity.com/paper/2312.03543/) (2023)
- [Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving](https://mlsanity.com/paper/2203.00858/) (2022)
- [Global Feature Aggregation for Accident Anticipation](https://mlsanity.com/paper/2006.08942/) (2020)
- [Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents](https://mlsanity.com/paper/2108.00273/) (2021)

## Abstract (arXiv)

While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high performance, exhibit significant instability in predictions and latent representations when faced with minor input perturbations, posing serious reliability risks. To address this, we introduce SECURE - Stable Early Collision Understanding Robust Embeddings, a framework that formally defines and enforces model robustness. SECURE is founded on four key attributes: consistency and stability in both prediction space and latent feature space. We propose a principled training methodology that fine-tunes a baseline model using a multi-objective loss, which minimizes divergence from a reference model and penalizes sensitivity to adversarial perturbations. Experiments on DAD and CCD datasets demonstrate that our approach not only significantly enhances robustness against various perturbations but also improves performance on clean data, achieving new state-of-the-art results.