Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA
In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios. We describe how we use CARLA, a realistic urban driving simulator, to create these scenarios, and how we use ShapeShifter to generate content-preserving attacks against those scenarios.
Code (3)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning
Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual fe…
Phishing Website DetectionImproving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlations
Machine learning (ML) has demonstrated significant advancements in Android malware detection (AMD); however, the resilience of ML against realistic evasion attacks remains a major obstacle for AMD. One of the primary fac…
Adversarial RobustnessAndroid Malware DetectionDomain AdaptationMalware DetectionAgainst All Odds: Winning the Defense Challenge in an Evasion Competition with Diversification
Machine learning-based systems for malware detection operate in a hostile environment. Consequently, adversaries will also target the learning system and use evasion attacks to bypass the detection of malware. In this pa…
AllBIG-bench Machine LearningMalware DetectionExplanation-Guided Diagnosis of Machine Learning Evasion Attacks
Machine Learning (ML) models are susceptible to evasion attacks. Evasion accuracy is typically assessed using aggregate evasion rate, and it is an open question whether aggregate evasion rate enables feature-level diagno…
BIG-bench Machine LearningOpen-Ended Question AnsweringURET: Universal Robustness Evaluation Toolkit (for Evasion)
Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustn…
image-classificationImage Classification