Bakary Badjie, LASIGE’s PhD student, published a paper titled “Adversarial Attacks and Countermeasures on Image Classification-based Deep Learning Models in Autonomous Driving Systems: A Systematic Review”, in the ACM Computing Surveys (CSUR) Journal, a top-ranked journal with an impact factor of 23.8, ranked 6.280 in SCImago Journal Rank and 1/143 in Scimago’s Computer Science and Methods Category. The paper co-authors are LASIGE’s integrated researchers José Cecílio and António Casimiro.

The paper provides a systematic review that offers an up-to-date analysis of the complexities of adversarial attacks and the limitations of the existing countermeasures, especially against adaptive and transfer-based attacks. It provides an in-depth understanding of the evolving landscape of adversarial machine learning (AML). The paper also discusses the need for robust defenses to enhance the evolution of autonomous driving technology, focusing on offering guidelines and recommendations for developing more resilient image classification deep learning models for autonomous driving systems.

The full paper is available at: https://doi.org/10.1145/3691625