Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models
This addresses fairness issues in AI systems for societal applications like hiring and criminal justice, offering a flexible solution for deployed models where retraining is not feasible.
The paper tackles the problem of mitigating bias in deployed deep learning models without retraining by proposing fairness-aware adversarial perturbation (FAAP), which perturbs input data to blind models on fairness-related features, achieving effective performance in experimental evaluations and real-world deployments.
Prioritizing fairness is of central importance in artificial intelligence (AI) systems, especially for those societal applications, e.g., hiring systems should recommend applicants equally from different demographic groups, and risk assessment systems must eliminate racism in criminal justice. Existing efforts towards the ethical development of AI systems have leveraged data science to mitigate biases in the training set or introduced fairness principles into the training process. For a deployed AI system, however, it may not allow for retraining or tuning in practice. By contrast, we propose a more flexible approach, i.e., fairness-aware adversarial perturbation (FAAP), which learns to perturb input data to blind deployed models on fairness-related features, e.g., gender and ethnicity. The key advantage is that FAAP does not modify deployed models in terms of parameters and structures. To achieve this, we design a discriminator to distinguish fairness-related attributes based on latent representations from deployed models. Meanwhile, a perturbation generator is trained against the discriminator, such that no fairness-related features could be extracted from perturbed inputs. Exhaustive experimental evaluation demonstrates the effectiveness and superior performance of the proposed FAAP. In addition, FAAP is validated on real-world commercial deployments (inaccessible to model parameters), which shows the transferability of FAAP, foreseeing the potential of black-box adaptation.