相关论文: Black-Box Audits for Group Distribution Shifts

As artificial intelligence plays an increasingly substantial role in decisions affecting humans and society, the accountability of automated decision systems has been receiving increasing attention from researchers and practitioners.…

Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes (e.g., the number of convolutional layers) of a target black-box model can be exposed through a sequence of…

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

Sentiment detection is an important building block for multiple information retrieval tasks such as product recommendation, cyberbullying detection, and misinformation detection. Unsurprisingly, multiple commercial APIs, each with different…

Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize…

Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection.…

With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models. In…

Given an algorithmic predictor that is "fair" on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound? In this paper, we study the transferability of statistical…

The recent explosive growth in Deep Neural Networks applications raises concerns about the black-box usage of such models, with limited trasparency and trustworthiness in high-stakes domains, which have been crystallized as regulatory…

We developed a tool for detecting domain shifts, namely subtle differences in the probability distributions of datasets. We identify these shifts using an algorithm designed to detect localised density anomalies in high-dimensional feature…

We initiate the study of proper losses for evaluating generative models in the discrete setting. Unlike traditional proper losses, we treat both the generative model and the target distribution as black-boxes, only assuming ability to draw…

Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interests of a specific principal while appearing to operate normally. We construct the first…

Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a…

Randomized controlled trials (RCTs) are the gold standard for evaluating causal effects but are often costly and difficult to scale; consequently, they are frequently augmented with auxiliary external controls in many applications. Prior…

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain…

We show how any PAC learning algorithm that works under the uniform distribution can be transformed, in a blackbox fashion, into one that works under an arbitrary and unknown distribution $\mathcal{D}$. The efficiency of our transformation…

As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool image classification models without access to model structure…

With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…