United States

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker&#39;s knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion attacks. However, attackers may not know what the model is used for in practice. We propose a generative adversarial network (GAN) based method to explore likely or similar domains of a target model -- the model domain inference (MDI) attack. For a given target (classification) model, we assume that the attacker knows nothing but the input and output formats and can use the model to derive the prediction for any input in the desired form. Our basic idea is to use the target model to affect a GAN training process for a candidate domain&#39;s dataset that is easy to obtain. We find that the target model may distort the training procedure less if the domain is more similar to the target domain. We then measure the distortion level with the distance between GAN-generated datasets, which can be used to rank candidate domains for the target model. Our experiments show that the auxiliary dataset from an MDI top-ranked domain can effectively boost the result of model-inversion attacks. 

AAAI 2023

GAN-based Domain Inference Attack

membership inference attacks

model-based attacks

model inversion attacks

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion attacks. However, attackers may not know what the model is used for in practice. We propose a generative adversarial network (GAN) based method to explore likely or similar domains of a target model -- the model domain inference (MDI) attack. For a given target (classification) model, we assume that the attacker knows nothing but the input and output formats and can use the model to derive the prediction for any input in the desired form. Our basic idea is to use the target model to affect a GAN training process for a candidate domain's dataset that is easy to obtain. We find that the target model may distort the training procedure less if the domain is more similar to the target domain. We then measure the distortion level with the distance between GAN-generated datasets, which can be used to rank candidate domains for the target model. Our experiments show that the auxiliary dataset from an MDI top-ranked domain can effectively boost the result of model-inversion attacks. 

poster

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

Traffic congestion event prediction is an important yet challenging task in intelligent transportation systems. Many existing works about traffic prediction integrate various temporal encoders and graph convolution networks (GCNs), called spatio-temporal graph-based neural networks, which focus on predicting dense variables such as flow, speed and demand in time snapshots, but they can hardly forecast the traffic congestion events that are sparsely distributed on the continuous time axis. In recent years, neural point process (NPP) has emerged as an appropriate framework for event prediction in continuous time scenarios. However, most conventional works about NPP cannot model the complex spatio-temporal dependencies and congestion evolution patterns. To address these limitations, we propose a spatio-temporal graph neural point process framework, named STGNPP for traffic congestion event prediction. Specifically, we first design the spatio-temporal graph learning module to fully capture the long-range spatio-temporal dependencies from the historical traffic state data along with the road network. The extracted spatio-temporal hidden representation and congestion event information are then fed into a continuous gated recurrent unit to model the congestion evolution patterns. In particular, to fully exploit the periodic information, we also improve the intensity function calculation of the point process with a periodic gated mechanism. Finally, our model simultaneously predicts the occurrence time and duration of the next congestion. Extensive experiments on two real-world datasets demonstrate that our method achieves superior performance in comparison to existing state-of-the-art approaches.

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

By harnessing the latest advances in deep learning, image-to-image translation architectures have recently achieved impressive capabilities. Unfortunately, the growing representational power of these architectures has prominent unethical uses. Among these, the threats of (1) face manipulation ("DeepFakes") used for misinformation or pornographic use (2) "DeepNude" manipulations of body images to remove clothes from individuals, etc. Several works tackle the task of disrupting such image translation networks by inserting imperceptible adversarial attacks into the input image. Nevertheless, these works have limitations that may result in disruptions that are not practical in the real world. Specifically, most works generate disruptions in a white-box scenario, assuming perfect knowledge about the image translation network. The few remaining works that assume a black-box scenario require a large number of queries to successfully disrupt the adversary's image translation network. In this work we propose Leaking Transferable Perturbations (LTP), an algorithm that significantly reduces the number of queries needed to disrupt an image translation network by dynamically re-purposing previous disruptions into new query efficient disruptions.

Practical Disruption of Image Translation Deepfake Networks

Accuracy and individual fairness are both crucial for trustworthy machine learning, but these two aspects are often incompatible with each other so that enhancing one aspect may sacrifice the other inevitably with side effects of true bias or false fairness. We propose in this paper a new fairness criterion, accurate fairness, to align individual fairness with accuracy. Informally, it requires the treatments of an individual and the individual's similar counterparts to conform to a uniform target, i.e., the ground truth of the individual. We prove that accurate fairness also implies typical group fairness criteria over a union of similar sub-populations. We then present a Siamese fairness in-processing approach to minimize the accuracy and fairness losses of a machine learning model under the accurate fairness constraints. To the best of our knowledge, this is the first time that a Siamese approach is adapted for bias mitigation. We also propose fairness confusion matrix-based metrics, fair-precision, fair-recall, and fair-F1 score, to quantify a trade-off between accuracy and individual fairness. Comparative case studies with popular fairness datasets show that our Siamese fairness approach can achieve on average 1.02%-8.78% higher individual fairness (in terms of fairness through awareness) and 8.38%-13.69% higher accuracy, as well as 10.09%-20.57% higher true fair rate, and 5.43%-10.01% higher fair-F1 score, than the state-of-the-art bias mitigation techniques. This demonstrates that our Siamese fairness approach can indeed improve individual fairness without trading accuracy. Finally, the accurate fairness criterion and Siamese fairness approach are applied to mitigate the possible service discrimination with a real Ctrip dataset, by on average fairly serving 112.33% more customers (specifically, 81.29% more customers in an accurately fair way) than baseline models.

Accurate Fairness: Improving Individual Fairness without Trading Accuracy

Non-Pharmaceutical Interventions (NPIs), such as social gathering restrictions, have shown effectiveness to slow the transmission of COVID-19 by reducing the contact of people. To support policy-makers, multiple studies have first modelled human mobility via macro indicators (e.g., average daily travel distance) and then study the effectiveness of NPIs. In this work, we focus on mobility modelling and, from a micro perspective, aim to predict locations that will be visited by COVID-19 cases. Since NPIs generally cause economic and societal loss, such a prediction benefits governments when they design and evaluate them. However, in real-world situations, strict privacy data protection regulations result in severe data sparsity problems (i.e., limited case and location information).
To address these challenges and jointly model variables including a geometric graph, a set of diffusions and a set of locations, we propose a model named Deep Graph Diffusion Infomax (DGDI). We show the maximization of DGDI can be bounded by two tractable components: a univariate Mutual Information (MI) between geometric graph and diffusion representation, and a univariate MI between diffusion representation and location representation. To facilitate the research of COVID-19 prediction, we present two benchmarks that contain geometric graphs and location histories of COVID-19 cases. Extensive experiments on the two benchmarks show that DGDI significantly outperforms other competing methods.

Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax

Counterfactuals are often described as 'retrospective,' focusing on hypothetical alternatives to a realized past. This description relates to an often implicit assumption about the structure and stability of exogenous variables in the system being modeled –– an assumption that is reasonable in many settings where counterfactuals are used. In this work, we consider cases where we might reasonably make a different assumption about exogenous variables, namely, that the exogenous noise terms of each unit do exhibit some unit-specific structure and/or stability. This leads us to a different use of counterfactuals — a 'forward-looking' rather than 'retrospective' counterfactual. We introduce "counterfactual treatment choice," a type of treatment choice problem that motivates using forward-looking counterfactuals. We then explore how mismatches between interventional versus forward-looking counterfactual approaches to treatment choice, consistent with different assumptions about exogenous noise, can lead to counterintuitive results.

Counterfactuals for the Future

AI systems can create, propagate, support, and automate bias in decision-making processes. To mitigate biased decisions, we both need to understand the origin of the bias and define what it means for an algorithm to make fair decisions. Most group fairness notions assess a model's equality of outcome by computing statistical metrics on the outputs. We argue that these output metrics encounter intrinsic obstacles and present a complementary approach that aligns with the increasing focus on equality of treatment. By Locating Unfairness through Canonical Inverse Design (LUCID), we generate a canonical set that shows the desired inputs for a model given a preferred output. The canonical set reveals the model's internal logic and exposes potential unethical biases by repeatedly interrogating the decision-making process. We evaluate LUCID on the UCI Adult and COMPAS data sets and find that some biases detected by a canonical set differ from those of output metrics. The results show that by shifting the focus towards equality of treatment and looking into the algorithm's internal workings, the canonical sets are a valuable addition to the toolbox of algorithmic fairness evaluation.



LUCID: Exposing Bias through Inverse Design

Access to high-quality maternal health care services is limited in Kenya, which resulted in ∼36,000 maternal and neonatal deaths in 2018. To tackle this challenge, Jacaranda Health (a non-profit organization working on maternal health in Kenya) developed PROMPTS, an SMS based tele-triage system for pregnant and puerperal women, which has more than 350,000 active users in Kenya. PROMPTS empowers pregnant women living far away from doctors and hospitals to send SMS messages to get quick answers (through human helpdesk agents) to questions about their medical symptoms and pregnancy status. Unfortunately, ∼1.1 million SMS messages are received by PROMPTS every month, which makes it challenging for helpdesk agents to ensure that these messages can be interpreted correctly and evaluated by their level of emergency to ensure timely responses and/or treatments for women in need. This paper reports on a collaborative effort with Jacaranda Health to develop a state-of-the-art natural language processing (NLP) framework, TRIM-AI (TRIage for Mothers using AI), which can automatically predict the emergency level (or severity of medical condition) of a pregnant mother based on the content of their SMS messages. TRIM-AI leverages recent advances in multi-lingual pre-training and continual pre-training to tackle code-mixed SMS messages (between English and Swahili), and achieves a weighted F1 score of 0.774 on real-world datasets. TRIMAI has been successfully deployed in the field since June 2022, and is being used by Jacaranda Health to prioritize the provision of services and care to pregnant women with the most critical medical conditions. Our preliminary A/B tests in the field show that TRIM-AI is ∼17% more accurate at predicting high-risk medical conditions from SMS messages sent by pregnant Kenyan mothers, which reduces the helpdesk’s workload by ∼12%.

A Continual Pre-training Approach to Tele-Triaging Pregnant Women in Kenya

Anti-money laundering (AML) systems play a critical role in safeguarding global economy. As money laundering is considered as one of the top group crimes, there is a crucial need to discover money laundering sub-network behind a particular money laundering transaction for a robust AML system. However, existing rule-based methods for money laundering sub-network discovery is heavily based on domain knowledge and may lag behind the modus operandi of launderers. Therefore, in this work, we first address the money laundering sub-network discovery problem with a neural network based approach, and propose an AML framework AMAP equipped with an adaptive sub-network proposer. In particular, we design an adaptive sub-network proposer guided by a supervised contrastive loss to discriminate money laundering transactions from massive benign transactions. We conduct extensive experiments on real-word datasets in AliPay of Ant Group. The result demonstrates the effectiveness of our AMAP in both money laundering transaction detection and money laundering sub-network discovering. The learned framework which yields money laundering sub-network from massive transaction network leads to a more comprehensive risk coverage and a deeper insight to money laundering strategies.

Towards Learning to Discover Money Laundering Sub-network in Massive Transaction Network

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show that some of the examples in the augmented dataset can be not important or even harmful to fairness. We hence propose a general method for pruning both the factual and counterfactual examples to maximize the model’s fairness as measured by the demographic parity, equality of opportunity, and equality of odds. The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset. Our experiments are conducted using models of varying sizes and pre-training settings.

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

The desired output for most real-world tasks using machine learning (ML) and remote sensing data is a set of dense predictions that form a predicted map for a geographic region. However, most prior work involving ML and remote sensing follows the traditional practice of reporting metrics on a set of independent, geographically-sparse samples and does not perform dense predictions. To reduce the labor of producing dense prediction maps, we present OpenMapFlow---an open-source python library for rapid map creation with ML and remote sensing data. OpenMapFlow provides 1) a data processing pipeline for users to create labeled datasets for any region, 2) code to train state-of-the-art deep learning models on custom or existing datasets, and 3) a cloud-based architecture to deploy models for efficient map prediction. We demonstrate the benefits of OpenMapFlow through experiments on three binary classification tasks: cropland, crop type (maize), and building mapping. We show that OpenMapFlow drastically reduces the time required for dense prediction compared to traditional workflows. We hope this library will stimulate novel research in areas such as domain shift, unsupervised learning, and societally-relevant applications and lessen the barrier to adopting research methods for real-world tasks.

GAN-based Domain Inference Attack

Downloads

Next from AAAI 2023

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

Similar lecture

Canary Extraction in Natural Language Understanding Models