ScoreCAM and Segmentation-Based Adversarial Attacks in Autonomous Vehicles
Bibliographic record
Abstract
Machine learning (ML) has become essential for tasks like detection and classification in autonomous vehicles (AVs). However, ML models are vulnerable to adversarial attacks, which can weaken passenger trust and raise safety concerns in autonomous driving systems. This is especially critical in systems like traffic sign recognition (TSR), where a misclassification caused by an adversarial attack could lead to serious safety risks. This research work explored the vulnerabilities of TSR models to adversarial attacks focusing on projected gradient descent (PGD) and the fast gradient sign method (FGSM). An adversarial attack pipeline is proposed that leverages ScoreCAM-based region-of-interest (ROI) localization to enhance the effectiveness of these attacks. Adversarial attacks manipulate the input data to mislead the models, achieving a high attack success rate (ASR) by exploiting their vulnerabilities. Experimental results on multiple models such as VGG19, convolutional neural network (CNN), ResNet50 and vision transformers (ViT) demonstrate significant increases in ASR. For instance, our method achieved a 97.67% ASR using PGD on VGG19 and a 95.89% ASR using FGSM on the same model, marking a considerable performance gain over traditional approaches. Moreover, these results are achieved with high computational efficiency, with average query times as low as 69.8 milliseconds.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".