paper-with-me

홈 › Papers

Enhancing Transparency and Control when Drawing Data-Driven Inferences about Individuals

2016-06-26 · Daizhuo Chen, Samuel P. Fraiberger, Robert Moakler, Foster Provost

Recent studies have shown that information disclosed on social network sites (such as Facebook) can be used to predict personal characteristics with surprisingly high accuracy. In this paper we examine a method to give online users transparency into why certain inferences are made about them by statistical models, and control to inhibit those inferences by hiding ("cloaking") certain personal information from inference. We use this method to examine whether such transparency and control would be a reasonable goal by assessing how difficult it would be for users to actually inhibit inferences. Applying the method to data from a large collection of real users on Facebook, we show that a user must cloak only a small portion of her Facebook Likes in order to inhibit inferences about their personal characteristics. However, we also show that in response a firm could change its modeling of users to make cloaking more difficult.

📄 PDF Abstract BibTeX arXiv:1606.08063

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models

2025-03-25 · Bowei Tian, Xuntao Lyu, Meng Liu, Hongyi Wang 외

Representation Engineering (RepE) has emerged as a powerful paradigm for enhancing AI transparency by focusing on high-level representations rather than individual neurons or circuits. It has proven effective in improvin…

DescriptiveFairness

Logic, Optimization, and Artificial Intelligence

2026-07-17 · J. N. Hooker arxiv

Logic and optimization can, in combination, make valuable contributions to rule-based AI. Logic is the obvious medium for encoding a rule base and drawing inferences from it, while optimization provides a powerful techno…

DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks

2025-12-01 · Hyunjun Kim, Sooyoung Ryu arxiv

As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents b…

Spatial Reasoning

Designing and Evaluating an Educational Recommender System with Different Levels of User Control

2025-01-22 · Qurat Ul Ain, Mohamed Amine Chatti, William Kana Tsoplefack, Rawaa Alatrash 외

Educational recommender systems (ERSs) play a crucial role in personalizing learning experiences and enhancing educational outcomes by providing recommendations of personalized resources and activities to learners, tailo…

Recommendation Systems

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding

2026-05-29 · Qian Kou, Xiaofeng Shi, Yulin Li, Xiaosong Qiu 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical engineering drawings, where high annotation…

Visual Question Answering