How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is a realistic scenario, where attackers have query-only access to the target model. Three properties are introduced to evaluate attack feasibility: robustness to compression, stealthiness to automatic detection, and stealthiness to human inspection. State-of-the-Art methods tend to prioritize one criterion at the expense of others. We propose ECLIPSE, a novel attack method employing Gaussian blurring on sampled gradients and a local surrogate model. Comprehensive experiments on a public dataset highlight ECLIPSE's advantages, demonstrating its contribution to the trade-off between the three properties.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesSimilar Papers 제목 키워드 기반
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settin…
Backdoor AttackData PoisoningBlack-box Stealthy GPS Attacks on Unmanned Aerial Vehicles
This work focuses on analyzing the vulnerability of unmanned aerial vehicles (UAVs) to stealthy black-box false data injection attacks on GPS measurements. We assume that the quadcopter is equipped with IMU and GPS senso…
Sensor FusionA Practical and Stealthy Adversarial Attack for Cyber-Physical Applications
Adversarial perturbations on misleading a well-trained machine learning (ML) model have been studied in computer vision (CV) and other related application areas. However, there is very limited focus on studying the impac…
Adversarial AttackStealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into considerat…
Face RecognitionBackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks…
Knowledge Distillation