paper-with-me

홈 › Papers

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

2023-05-31 · Hye-jin Shim, Rosa González Hautamäki, Md Sahidullah, Tomi Kinnunen

Shortcut learning, or Clever Hans effect refers to situations where a learning agent (e.g., deep neural networks) learns spurious correlations present in data, resulting in biased models. We focus on finding shortcuts in deep learning based spoofing countermeasures (CMs) that predict whether a given utterance is spoofed or not. While prior work has addressed specific data artifacts, such as silence, no general normative framework has been explored for analyzing shortcut learning in CMs. In this study, we propose a generic approach to identifying shortcuts by introducing systematic interventions on the training and test sides, including the boundary cases of near-perfect and worse than coin flip (label flip). By using three different models, ranging from classic to state-of-the-art, we demonstrate the presence of shortcut learning in five simulated conditions. We analyze the results using a regression model to understand how biases affect the class-conditional score statistics.

📄 PDF Abstract BibTeX arXiv:2306.00044

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents

2026-02-26 · Dhwanil M. Mori, Neil F. Johnson arxiv

Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources such as energy, bandwidth, or computing power. We study a simplified version of this settin…

On the Detection of Mixture Distributions with applications to the Most Biased Coin Problem

2016-03-25 · Kevin Jamieson, Daniel Haas, Ben Recht

This paper studies the trade-off between two different kinds of pure exploration: breadth versus depth. The most biased coin problem asks how many total coin flips are required to identify a "heavy" coin from an infinite…

Anomaly Detection

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning

2023-06-05 · Sam Lobel, Akhil Bagaria, George Konidaris

We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distr…

Montezuma's Revengereinforcement-learningReinforcement Learning

A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements

2020-10-15 · Y. Yang, P. Xiao, B. Liao, N. Deligiannis

We propose a novel deep neural network, coined DeepFPC-$\ell_2$, for solving the 1-bit compressed sensing problem. The network is designed by unfolding the iterations of the fixed-point continuation (FPC) algorithm with …

compressed sensing

Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems

2026-04-16 · Xing Zhang, Guanghui Wang, Yanwei Cui, Wei Qiu 외 arxiv

Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku 4.5 (6 methods $\times$ 4 tasks $\times$ 3 repeats), 49% score below zero-shot; …