Algebraic Adversarial Attacks on Explainability Models
Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trace how an adversarial point was generated. In this work, we propose an algebraic approach to adversarial attacks and study the conditions under which one can generate adversarial examples for post-hoc explainability models. Phrasing neural networks in the framework of geometric deep learning, algebraic adversarial attacks are constructed through analysis of the symmetry groups of neural networks. Algebraic adversarial examples provide a mathematically tractable approach to adversarial examples. We validate our approach of algebraic adversarial examples on two well-known and one real-world dataset.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Algebraic Adversarial Attacks on Integrated Gradients
Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution …
Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models
The advent of social media has given rise to numerous ethical challenges, with hate speech among the most significant concerns. Researchers are attempting to tackle this problem by leveraging hate-speech detection and em…
Adversarial RobustnessDecision MakingHate Speech DetectionUKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, which are difficult to interpret by humans…
Adversarial AttackExplainable ModelsKnowledge GraphsPrediction+1Impact of Adversarial Attacks on Deep Learning Model Explainability
In this paper, we investigate the impact of adversarial attacks on the explainability of deep learning models, which are commonly criticized for their black-box nature despite their capacity for autonomous feature extrac…
Decision MakingDeep LearningExplainability-Based Adversarial Attack on Graphs Through Edge Perturbation
Despite the success of graph neural networks (GNNs) in various domains, they exhibit susceptibility to adversarial attacks. Understanding these vulnerabilities is crucial for developing robust and secure applications. In…
Adversarial AttackNode Classification