paper-with-me

Papers

Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models

2023-05-29 · Pranath Reddy Kumbam, Sohaib Uddin Syed, Prashanth Thamminedi, Suhas Harish, Ian Perera, Bonnie J. Dorr

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 employing language models to automatically moderate content and promote civil discourse. Unfortunately, recent studies have revealed that hate-speech detection systems can be misled by adversarial attacks, raising concerns about their resilience. While previous research has separately addressed the robustness of these models under adversarial attacks and their interpretability, there has been no comprehensive study exploring their intersection. The novelty of our work lies in combining these two critical aspects, leveraging interpretability to identify potential vulnerabilities and enabling the design of targeted adversarial attacks. We present a comprehensive and comparative analysis of adversarial robustness exhibited by various hate-speech detection models. Our study evaluates the resilience of these models against adversarial attacks using explainability techniques. To gain insights into the models' decision-making processes, we employ the Local Interpretable Model-agnostic Explanations (LIME) framework. Based on the explainability results obtained by LIME, we devise and execute targeted attacks on the text by leveraging the TextAttack tool. Our findings enhance the understanding of the vulnerabilities and strengths exhibited by state-of-the-art hate-speech detection models. This work underscores the importance of incorporating explainability in the development and evaluation of such models to enhance their resilience against adversarial attacks. Ultimately, this work paves the way for creating more robust and reliable hate-speech detection systems, fostering safer online environments and promoting ethical discourse on social media platforms.

📄 PDF Abstract BibTeX arXiv:2305.18585

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessDecision MakingHate Speech Detection

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

Algebraic Adversarial Attacks on Explainability Models

2025-03-16 · Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng 외

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…

Using Explainabilty to Detect Adversarial Attacks

2019-09-25 · Ohad Amosy and Gal Chechik

Deep learning models are often sensitive to adversarial attacks, where carefully-designed input samples can cause the system to produce incorrect decisions. Here we focus on the problem of detecting attacks, rather than …

Robust classification

Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks

2020-12-21 · Chenchen Zhao, Hao Li

Convolutional neural networks (CNN) have been more and more applied in mobile robotics such as intelligent vehicles. Security of CNNs in robotics applications is an important issue, for which potential adversarial attack…

Adversarial AttackDimensionality Reduction

Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous

2023-11-10 · Ziwei Wang, Nabil Aouf, Jose Pizarro, Christophe Honvault

Research on developing deep learning techniques for autonomous spacecraft relative navigation challenges is continuously growing in recent years. Adopting those techniques offers enhanced performance. However, such appro…

Adversarial AttackAdversarial Attack DetectionPose Estimation

UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA

2022-08-19 · Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner, Sewin Tariverdian 외

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+1