2024 · 12 citations · 24 references
ComputingComputer ScienceCybersecurityArtificial IntelligenceComputer SecurityMachine LearningAdversary TechniquesDeep LearningOptimization For Machine LearningPattern RecognitionThreat DetectionAdversarial RobustnessDeceptive BehaviorMachine-learning AttacksNatural Light ExposureRobustnessRobustness Of Ai SystemsSecurity Of Ai SystemsTraffic Sign Detection
Common illumination sources like sunlight or artificial light may introduce hidden vulnerabilities to AI systems. Our paper delves into these potential threats, offering a novel approach to simulate varying light conditions, including sunlight, headlights, and flashlight illuminations. Moreover, unlike typical physical adversarial attacks requiring conspicuous alterations, our method utilizes a model-agnostic black-box attack integrated with the Zeroth Order Optimization (ZOO) algorithm to identify deceptive patterns in a physically-applicable space. Consequently, attackers can recreate these simulated conditions, deceiving machine learning models with seemingly natural light. Empirical results demonstrate the efficacy of our method, misleading models trained on the GTSRB and LISA datasets under natural-like physical environments with an attack success rate exceeding 70% across all digital datasets, and remaining effective against all evaluated real-world traffic signs. Importantly, after adversarial training using samples generated from our approach, models showcase enhanced robustness, underscoring the dual value of our work in both identifying and mitigating potential threats. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
24
Explaining and Harnessing Adversarial Examples
Ian Goodfellow, Jonathon Shlens, Christian Szegedy · arXiv (Cornell University) · 2014 · 8.2K citations · Full text
Practical Black-Box Attacks against Machine Learning
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow et al. · 2017 · 3.5K citations
Robust Physical-World Attacks on Deep Learning Visual Classification
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes et al. · 2018 · 2.1K citations
Pin‐Yu Chen, Huan Zhang, Yash Sharma et al. · 2017 · 1.7K citations · Full text