BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal model representations not to encode sensitive information, which has the effect of pushing downstream predictors towards exhibiting demographic parity with respect to the sensitive information. The net result is that these BriarPatches provide an intervention mechanism available at user level, and complements prior research on fair representations that were previously only applicable by model developers and ML experts.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Towards Controllable Biases in Language Generation
We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text whe…
Dialogue GenerationText GenerationMitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding
Face recognition (FR) systems are often prone to demographic biases, partially due to the entanglement of demographic-specific information with identity-relevant features in facial embeddings. This bias is extremely crit…
Face VerificationFace RecognitionThe Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
Large language models (LLMs) form implicit beliefs (posteriors over latent variables) from prompts, but we lack a mechanistic account of how these beliefs are encoded in representation space, how they update with new evi…
Intervention Design for Effective Sim2Real Transfer
The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal inference, positioning domain randomizatio…
Causal InferenceData AugmentationA New Paradigm for Counterfactual Reasoning in Fairness and Recourse
Counterfactuals and counterfactual reasoning underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is t…
counterfactualCounterfactual ReasoningFairness