Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models
The distribution of child sexual abuse imagery (CSAI) is an ever-growing concern of our modern world; children who suffered from this heinous crime are revictimized, and the growing amount of illegal imagery distributed overwhelms law enforcement agents (LEAs) with the manual labor of categorization. To ease this burden researchers have explored methods for automating data triage and detection of CSAI, but the sensitive nature of the data imposes restricted access and minimal interaction between real data and learning algorithms, avoiding leaks at all costs. In observing how these restrictions have shaped the literature we formalize a definition of "Proxy Tasks", i.e., the substitute tasks used for training models for CSAI without making use of CSA data. Under this new terminology we review current literature and present a protocol for making conscious use of Proxy Tasks together with consistent input from LEAs to design better automation in this field. Finally, we apply this protocol to study -- for the first time -- the task of Few-shot Indoor Scene Classification on CSAI, showing a final model that achieves promising results on a real-world CSAI dataset whilst having no weights actually trained on sensitive data.
Code (0)
등록된 구현이 없습니다.
Tasks
Data InteractionScene ClassificationSimilar Papers 제목 키워드 기반
Robustness and risk-sensitivity in Markov decision processes
We uncover relations between robust MDPs and risk-sensitive MDPs. The objective of a robust MDP is to minimize a function, such as the expectation of cumulative cost, for the worst case when the parameters have uncertai…
SensitivityHedging of defaultable claims in a structural model using a locally risk-minimizing approach
In the context of a locally risk-minimizing approach, the problem of hedging defaultable claims and their Follmer-Schweizer decompositions are discussed in a structural model. This is done when the underlying process is …
A Model-Based Method for Minimizing CVaR and Beyond
We develop a variant of the stochastic prox-linear method for minimizing the Conditional Value-at-Risk (CVaR) objective. CVaR is a risk measure focused on minimizing worst-case performance, defined as the average of the …
Local risk-minimization for Barndorff-Nielsen and Shephard models
We obtain explicit representations of locally risk-minimizing strategies of call and put options for the Barndorff-Nielsen and Shephard models, which are Ornstein--Uhlenbeck-type stochastic volatility models. Using Malli…
Adversarial Surrogate Risk Bounds for Binary Classification
A central concern in classification is the vulnerability of machine learning models to adversarial attacks. Adversarial training is one of the most popular techniques for training robust classifiers, which involves minim…
Binary ClassificationClassification