Attribution-driven Causal Analysis for Detection of Adversarial Examples
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally masking high attribution features. We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood. Our study indicates that benign inputs are robust to the masking of high attribution features but adversarial inputs generated by the state-of-the-art adversarial attack methods such as DeepFool, FGSM, CW and PGD, are not robust to such masking. Further, our study demonstrates that this concentration of high-attribution features responsible for the incorrect decision is more pronounced in physically realizable adversarial examples. This difference in attribution of benign and adversarial inputs can be used to detect adversarial examples. Such a defense approach is independent of training data and attack method, and we demonstrate its effectiveness on digital and physically realizable perturbations.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackBIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes
Detecting offensive memes is crucial, yet standard deep neural network systems often remain opaque. Various input attribution-based methods attempt to interpret their behavior, but they face challenges with implicitly of…
Rethinking Spatio-Temporal Anomaly Detection: A Vision for Causality-Driven Cybersecurity
As cyber-physical systems grow increasingly interconnected and spatially distributed, ensuring their resilience against evolving cyberattacks has become a critical priority. Spatio-Temporal Anomaly detection plays an imp…
Anomaly DetectionGraph LearningAttribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models
Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity ta…
Network Intrusion DetectionRepresentation LearningAttribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce \textbf{Attribution Graphs} (AGs), which extend GradCAM++ to circuit-level representations, and \textbf{Causal Prob…
Adversarial RobustnessCausal-driven attribution (CDA): Estimating channel influence without user-level data
Attribution modelling lies at the heart of marketing effectiveness, yet most existing approaches depend on user-level path data, which are increasingly inaccessible due to privacy regulations and platform restrictions. T…