Attack-Agnostic Adversarial Detection
The growing number of adversarial attacks in recent years gives attackers an advantage over defenders, as defenders must train detectors after knowing the types of attacks, and many models need to be maintained to ensure good performance in detecting any upcoming attacks. We propose a way to end the tug-of-war between attackers and defenders by treating adversarial attack detection as an anomaly detection problem so that the detector is agnostic to the attack. We quantify the statistical deviation caused by adversarial perturbations in two aspects. The Least Significant Component Feature (LSCF) quantifies the deviation of adversarial examples from the statistics of benign samples and Hessian Feature (HF) reflects how adversarial examples distort the landscape of the model's optima by measuring the local loss curvature. Empirical results show that our method can achieve an overall ROC AUC of 94.9%, 89.7%, and 94.6% on CIFAR10, CIFAR100, and SVHN, respectively, and has comparable performance to adversarial detectors trained with adversarial examples on most of the attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAdversarial Attack DetectionAnomaly DetectionSimilar Papers 제목 키워드 기반
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or kn…
Adversarial AttackModel Agnostic Defense against Adversarial Patch Attacks on Object Detection in Unmanned Aerial Vehicles
Object detection forms a key component in Unmanned Aerial Vehicles (UAVs) for completing high-level tasks that depend on the awareness of objects on the ground from an aerial perspective. In that scenario, adversarial pa…
Objectobject-detectionObject DetectionAttack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
Explainable machine learning has become increasingly prevalent, especially in healthcare where explainable models are vital for ethical and trusted automated decision making. Work on the susceptibility of deep learning m…
Adversarial AttackAnomaly DetectionBIG-bench Machine LearningDecision Making+1Model-Agnostic Defense for Lane Detection against Adversarial Attack
Susceptibility of neural networks to adversarial attack prompts serious safety concerns for lane detection efforts, a domain where such models have been widely applied. Recent work on adversarial road patches have succes…
Adversarial AttackAutonomous DrivingLane DetectionA Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison
Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of a…
Compressive SensingAdversarial Attack