United States

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian et al., 2021) have shown that a robust model well-trained by AT exhibits a remarkable robustness disparity among classes, and propose various methods to obtain consistent robust accuracy across classes. Unfortunately, these methods sacrifice a good deal of the average robust accuracy. Accordingly, this paper proposes a novel framework of worst-class adversarial training and leverages no-regret dynamics to solve this problem. Our goal is to obtain a classifier with great performance on worst-class and sacrifice just a little average robust accuracy at the same time. We then rigorously analyze the theoretical properties of our proposed algorithm, and the generalization error bound in terms of the worst-class robust risk. Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies. Experiments on various datasets and networks show that our proposed method outperforms the state-of-the-art approaches.

AAAI 2023

WAT: Improve the Worst-class Robustness in Adversarial Training

worst-class robustness.

adversarial training

adversarial robustness

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.

poster

Monitoring machine learning models once they are deployed
is challenging. It is even more challenging to decide when
to retrain models in real-case scenarios when labeled data is
beyond reach, and monitoring performance metrics becomes
unfeasible. In this work, we use non-parametric bootstrapped
uncertainty estimates and SHAP values to provide explainable
uncertainty estimation as a technique that aims to monitor
the deterioration of machine learning models in deployment
environments, as well as determine the source of model deteri-
oration when target labels are not available. Classical methods
are purely aimed at detecting distribution shift, which can
lead to false positives in the sense that the model has not de-
teriorated despite a shift in the data distribution. To estimate
model uncertainty we construct prediction intervals using a
novel bootstrap method, which improves upon the work of
Kumar and Srivastava (2012). We show that both our model
deterioration detection system as well as our uncertainty es-
timation method achieve better performance than the current
state-of-the-art. Finally, we use explainable AI techniques to
gain an understanding of the drivers of model deterioration.
We release an open source Python package, doubt, which
implements our proposed methods, as well as the code used to
reproduce our experiments.

Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap

Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance. However, due to improvements in skeleton recognition algorithms as well as motion and depth sensors, more details of motion characteristics can be preserved in the skeleton dataset, leading to potential privacy leakage. We first train classifiers to categorize private information from skeleton trajectories to investigate the potential privacy leakage from skeleton datasets. Our preliminary experiments show that the gender classifier achieves 87% accuracy on average, and the re-identification classifier achieves 80% accuracy on average with three baseline models: Shift-GCN, MS-G3D, and 2s-AGCN. We propose an anonymization framework based on adversarial learning to protect potential privacy leakage from the skeleton dataset. Experimental results show that an anonymized dataset can reduce the risk of privacy leakage while having marginal effects on action recognition performance even with simple anonymizer architectures. The code used in our experiments is available at https://github.com/ml-postech/Skeleton-anonymization/

Anonymization for Skeleton Action Recognition

We present a new algorithm to train a robust malware detector. Malware is a prolific problem and malware detectors are a front-line defense. Modern detectors rely on machine learning algorithms. Now, the adversarial objective is to devise alterations to the malware code to decrease the chance of being detected whilst preserving the functionality and realism of the malware. Adversarial learning is effective in improving robustness but generating functional and realistic adversarial malware samples is non-trivial. Because: i) in contrast to tasks capable of using gradient-based feedback, adversarial learning in a domain without a differentiable mapping function from the problem space (malware code inputs) to the feature space is hard; and ii) it is difficult to ensure the adversarial malware is realistic and functional. 
This presents a challenge for developing scalable adversarial machine learning algorithms for large datasets at a production or commercial scale to realize robust malware detectors. We propose an alternative; perform adversarial learning in the feature space in contrast to the problem space. We prove the projection of perturbed, yet valid malware, in the problem space into feature space will always be a subset of adversarials generated in the feature space. Hence, by generating a robust network against feature-space adversarial examples, we inherently achieve robustness against problem-space adversarial examples. We formulate a Bayesian adversarial learning objective that captures the distribution of models for improved robustness. 
To explain the robustness of the Bayesian adversarial learning algorithm, we prove that our learning method bounds the difference between the adversarial risk and empirical risk and improves robustness. We show that Bayesian neural networks (BNNs) achieve state-of-the-art results; especially in the False Positive Rate (FPR) regime. Adversarially trained BNNs achieve state-of-the-art robustness. Notably, adversarially trained BNNs are robust against stronger attacks with larger attack budgets by a margin of up to 15% on a recent production-scale malware dataset of more than 20~million samples. Importantly, our efforts create a benchmark for future defenses in the malware domain.

Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness

It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for this is to perform temperature scaling, which adjusts the confidences of the predictions on any input by scaling the logits by a fixed value. Whilst this approach typically improves the average calibration across the whole test dataset, this improvement typically reduces the individual confidences of the predictions irrespective of whether the classification of a given input is correct or incorrect. With this insight, we base our method on the observation that different samples contribute to the calibration error by varying amounts, with some needing to increase their confidence and others needing to decrease it. Therefore, for each input, we propose to predict a different temperature value, allowing us to adjust the mismatch between confidence and accuracy at a finer granularity. Furthermore, we observe improved results on OOD detection and can also extract a notion of hardness for the data-points. Our method is applied post-hoc, consequently using very little computation time and with a negligible memory footprint and is applied to off-the-shelf pre-trained classifiers. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets, showing that producing per-data-point temperatures is beneficial also for the expected calibration error across the whole test set. Code is available at: this https URL.

Sample-dependent Adaptive Temperature Scaling for Improved Calibration

We consider partially observable Markov decision processes (POMDPs) modeling an agent that needs a supply of a certain resource (e.g. electricity stored in batteries) to operate safely. The resource is consumed by agent's action and can be replenished only in certain states. The agent aims to minimize the expected cost of reaching some goal while preventing resource exhaustion, a problem we call resource-safe goal optimization (RSGO). We take a two-step approach to the RSGO problem. First, using formal methods techniques, we design an algorithm computing a shield for a given scenario: a procedure that observes the agent and prevents it from using unsafe actions that might eventually lead to resource exhaustion. Second, we augment the POMCP heuristic search algorithm for POMDP planning with our shields to obtain an algorithm solving the RSGO problem. We implement our algorithm and present experiments showing its applicability to benchmarks from the literature.

Shielding in Resource-Constrained Goal POMDPs

Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, which is known as the robust fairness problem. Previously proposed Fair Robust Learning (FRL) adds regularization terms to penalize unfairness, but the performance on the better performed classes are decreased, leading to strong performance drop. In this paper, we observed two unfair phenomena during adversarial training: different difficulties in generating adversarial examples from each class (source-class fairness) and disparate target class tendencies when generating adversarial examples (target-class fairness). From the observations, we propose Balance Adversarial Training (BAT) to address the robust fairness problem. Regarding source-class fairness, we adjust the attack strength and difficulties of each class to generate samples near the decision boundary for easier and fairer model learning; considering target-class fairness, we encourage the adversarial example generation process towards each class with a fair tendency by introducing a uniform distribution constraint. Extensive experiments conducted on multiple datasets (CIFAR-10, CIFAR-100, and ImageNette) demonstrate that our method can significantly outperform other baselines in mitigating the robust fairness problem (+5-10\% on the worst class accuracy)

Improving Robust Fariness via Balance Adversarial Training

Despite being widely deployed in safety-critical applications such as autonomous driving and health care, deep neural networks (DNNs) still suffer from non-negligible reliability issues. Numerous works had reported that DNNs were vulnerable to either natural environmental noises or man-made adversarial noises.
How to repair DNNs in deployment with noisy samples is a crucial topic for the robustness of neural networks. While many network repairing methods based on data argumentation and weight adjustment have been proposed, they require retraining and redeploying the whole model, which causes high overhead and are infeasible for varying faulty cases on different deployment environments. In this paper, we propose a novel network repairing framework called PatchNAS from the architecture perspective, where we freeze the pretrained DNNs and introduce a small patch network to deal with failure samples at runtime. PatchNAS introduces a novel network instrumentation method to determine the faulty stage of the network structure given the collected failure samples. A small patch network structure is searched unsupervisedly using neural architecture search (NAS) technique with data samples from deployment environment.	The patch network repairs the DNNs by correcting the output feature maps of the faulty stage, which helps to maintain network performance on normal samples and enhance robustness in noisy environments. 	Extensive experiments based on several DNNs across 15 types of natural noises show that the proposed PatchNAS outperforms the state-of-the-arts with significant performance improvement as well as much lower deployment overhead.

PatchNAS: Repairing DNNs in Deployment with Patched Network Architecture Search

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be memorized by such trained models. Unfortunately, deleting information is out of the question as the data is already exposed to the Web or third-party platforms. Moreover, we cannot necessarily control the labeling process and the model trainings by other parties either. In this setting, we study the problem of targeted disinformation generation where the goal is to dilute the data and thus make a model safer and more robust against inference attacks on a specific target (e.g., a person's profile) by only inserting new data. Our method finds the closest points to the target in the input space that will be labeled as a different class. Since we cannot control the labeling process, we instead conservatively estimate the labels probabilistically by combining decision boundaries of multiple classifiers using data programming techniques. Our experiments show that a probabilistic decision boundary can be a good proxy for labelers, and that our approach is effective in defending against inference attacks and can scale to large data.

Redactor: A Data-centric and Individualized Defense Against Inference Attacks

Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and fi- nancial analysis have raised concerns regarding their reliability and trustworthiness. As automated systems become more mainstream, it is important their decisions be transparent, reliable and understandable by humans for better trust and confidence. To this effect, concept-based models such as Concept Bottleneck Models (CBMs) and Self-Explaining Neural Networks (SENN) have been proposed which constrain the latent space of a model to represent high level concepts easily understood by domain experts in the field. Although concept-based models promise a good approach to both increasing explainability and reliability, it is yet to be shown if they demonstrate robustness and output consistent concepts under systematic perturbations to their inputs. To better understand performance of concept-based models on curated malicious samples, in this paper, we aim to study their robustness to adversarial perturbations, which are also known as the imperceptible changes to the input data that are crafted by an attacker to fool a well-learned concept-based model. Specifically, we first propose and analyze different malicious attacks to evaluate the security vulnerability of concept based models. Subsequently, we propose a potential general adversarial training-based defense mechanism to increase robustness of these systems to the proposed malicious attacks. Extensive experiments on one synthetic and two real-world datasets demonstrate the effectiveness of the proposed attacks and the defense approach.

Understanding and Enhancing Robustness of Concept-based Models

Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can be added along arbitrary directions and the predicted labels of untargeted attacks should be unpredictable. However, we find that the naturally imbalanced inter-class semantic similarity makes those hard-class pairs become virtual targets of each other. This study investigates the impact of such closely-coupled classes on adversarial attacks and develops a self-paced reweighting strategy in adversarial training accordingly. Specifically, we propose to upweight hard-class pair losses in model optimization, which prompts learning discriminative features from hard classes. We further incorporate a term to quantify hard-class pair consistency in adversarial training, which greatly boosts model robustness. Extensive experiments show that the proposed adversarial training method achieves superior robustness performance over state-of-the-art defenses against a wide range of adversarial attacks. The code of the proposed SPAT is published at https://github.com/puerrrr/Self-Paced-Adversarial-Training.

Downloads

Next from AAAI 2023

Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap

Similar lecture

Improving Robust Fariness via Balance Adversarial Training