paper-with-me

Papers

A Neural Mean Embedding Approach for Back-door and Front-door Adjustment

2022-10-12 · Liyuan Xu, Arthur Gretton

We consider the estimation of average and counterfactual treatment effects, under two settings: back-door adjustment and front-door adjustment. The goal in both cases is to recover the treatment effect without having an access to a hidden confounder. This objective is attained by first estimating the conditional mean of the desired outcome variable given relevant covariates (the "first stage" regression), and then taking the (conditional) expectation of this function as a "second stage" procedure. We propose to compute these conditional expectations directly using a regression function to the learned input features of the first stage, thus avoiding the need for sampling or density estimation. All functions and features (and in particular, the output features in the second stage) are neural networks learned adaptively from data, with the sole requirement that the final layer of the first stage should be linear. The proposed method is shown to converge to the true causal parameter, and outperforms the recent state-of-the-art methods on challenging causal benchmarks, including settings involving high-dimensional image data.

📄 PDF Abstract BibTeX arXiv:2210.06610

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualDensity Estimationregression

Similar Papers 제목 키워드 기반

MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

2022-05-13 · Hang Wang, Zhen Xiang, David J. Miller, George Kesidis

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a bac…

Adversarial AttackBackdoor Attackbackdoor defenseVocal Bursts Type Prediction

Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire

2022-01-28 · Siddhartha Datta, Nigel Shadbolt

Malicious agents in collaborative learning and outsourced data collection threaten the training of clean models. Backdoor attacks, where an attacker poisons a model during training to successfully achieve targeted miscla…

Backdoor Attackbackdoor defense

Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks

2024-02-28 · Alexander Unnervik, Hatef Otroshi Shahreza, Anjith George, Sébastien Marcel

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoo…

Backdoor Attackopen-set classification

Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning

2022-10-20 · Xiaoyi Chen, Baisong Xin, Shengfang Zhai, Shiqing Ma 외

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-…

Backdoor AttackContrastive LearningSentenceSentence Embeddings+1

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

2025-01-05 · Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a …

backdoor defense