Edit StudentProjectForm: Towards robustness of post hoc Explainable AI methods

You do not have permission to edit this page, for the following reason:

The action you have requested is limited to users in the group: Users.

Summary:	MANDATORY: (provide a one-line* summary of the project)*
Programme:	OPTIONAL: (Name and the number of credits)
Keywords:	OPTIONAL: (Give 4-5 keywords)
TimeFrame:	MANDATORY: (Indicate time for the project, for example, Fall 2024)
References:	[1] Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "" Why should i trust you?" Explaining the predictions of any classifier." Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016. [2] Lundberg, S., and S. I. Lee. "A unified approach to interpreting model predictions. arXiv 2017." arXiv preprint arXiv:1705.07874 (2022). [3] Aïvodji, Ulrich, et al. "Fooling SHAP with Stealthily Biased Sampling." The Eleventh International Conference on Learning Representations. 2022. [4] Laberge, Gabriel, et al. "Fool SHAP with Stealthily Biased Sampling." arXiv preprint arXiv:2205.15419 (2022). [5] Slack, Dylan, et al. "Fooling lime and shap: Adversarial attacks on post hoc explanation methods." Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. 2020. [6] Friedman, Jerome H. "Greedy function approximation: a gradient boosting machine." Annals of statistics (2001): 1189-1232. [7] Simonyan, Karen, Andrea Vedaldi, and Andrew Zisserman. "Deep inside convolutional networks: Visualising image classification models and saliency maps." arXiv preprint arXiv:1312.6034 (2013). [8] Baniecki, Hubert, Wojciech Kretowicz, and Przemyslaw Biecek. "Fooling partial dependence via data poisoning." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2022. [9] Dimanov, Botty, et al. "You shouldn’t trust me: Learning models which conceal unfairness from multiple explanation methods." ECAI 2020. IOS Press, 2020. 2473-2480. [10] Saito, Sean, et al. "Improving lime robustness with smarter locality sampling." arXiv preprint arXiv:2006.12302 (2020). OPTIONAL: (Give 2-3 references for students to start with)
Prerequisites:	OPTIONAL: (Courses, any other important information)
Supervisor(s):	MANDATORY: (can be multiple names, coma-separated)
Examiner:	OPTIONAL: (Name of project Examiner)
Author(s):	OPTIONAL: (can be multiple names, coma-separated)
Level:	MANDATORY: choose one, preferably <Master>
Status:	MANDATORY: choose <Open> when the topic is ready for students to select

Project description (free text)

Give a concise project description. Include:

Research question
Whether it’s more software or hardware related
A very brief description of 3-4 work packages
Deliverables/outcomes/results

Post Hoc explanation methods like LIME [1] and SHAP [2], due to their internal perturbation mechanisms, are shown to be susceptible to adversarial attacks [3, 4]. This means that, for example, a biased method can be altered maliciously in a way to fool explanation methods so that it appears as unbiased [5]. Furthermore, there are methods for fooling Partial Dependence Plot (PDP)[6] and Gradient-Based approaches7], which propose attacks according to each method's weaknesses [8, 9]. Almost every industrial sector leans towards adopting AI. However, there is a barrier of trust to AI which can be alleviated by Explainable AI; therefore it is of immense importance to make XAI methods robust to adversarial attacks. This project aims at exploring and equipping a chosen Post hoc XAI method with a mechanism to make them robust to adversarial attacks [10].

Summary:

This is a minor edit Watch this page

Cancel

Edit StudentProjectForm: Towards robustness of post hoc Explainable AI methods

Navigation menu

Views

Personal tools

Search

Tools