Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a specific test instance is the target of a training-set attack. Target identification can be combined with adversarial-instance identification to find (and remove) the attack instances, mitigating the attack with minimal impact on other predictions. Rather than focusing on a single attack method or data modality, we build on influence estimation, which quantifies each training instance's contribution to a model's prediction. We show that existing influence estimators' poor practical performance often derives from their over-reliance on training instances and iterations with large losses. Our renormalized influence estimators fix this weakness; they far outperform the original estimators at identifying influential groups of training examples in both adversarial and non-adversarial settings, even finding up to 100% of adversarial training instances with no clean-data false positives. Target identification then simplifies to detecting test instances with anomalous influence values. We demonstrate our method's effectiveness on backdoor and poisoning attacks across various data domains, including text, vision, and speech, as well as against a gray-box, adaptive attacker that specifically optimizes the adversarial instances to evade our method. Our source code is available at https://github.com/ZaydH/target_identification.
Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To identify the susceptible classes we use distance-based measures and apply them on a trained model. Based on the distance among original classes, we create mapping among original classes and adversarial classes that helps to reduce the randomness of a model to a significant amount in an adversarial setting. We analyze the high dimensional geometry among the …
University of California, Irvine（加利福尼亚大学尔湾分校）；University of Oregon, Eugene（俄勒冈大学尤金分校）
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body of work on robust learning, which reduces vulnerability to these attacks, though sometimes at a high cost in compute time or accuracy. In this paper, we take an alternate approach -- we attempt to understand the attacker by analyzing adversarial text to determine which methods were used to create it. Our first contribution is an extensive dataset for attack …
We propose a novel method to capture data points near decision boundary in neural network that are often referred to a specific type of uncertainty. In our approach, we sought to perform uncertainty estimation based on the idea of adversarial attack method. In this paper, uncertainty estimates are derived from the input perturbations, unlike previous studies that provide perturbations on the model's parameters as in Bayesian approach. We are able to produce uncertainty with couple of perturbations on the inputs. Interestingly, we apply the proposed method to datasets derived from blockchain. W…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心 (DFKI)）；TU Kaiserslautern（凯泽斯劳滕工业大学）；NVIDIA Research（英伟达研究院）
In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness. For this purpose, we selectively retrain different portions of VGG and ResNet architectures on CIFAR-10, Imagenette, and ImageNet using non-adversarial and adversarial data. Experimental results show that susceptibility to adversarial samples is associated with low-level feature extraction layers. Therefore, retraining of high-level layers is insufficient for achieving robustness. Furthermore, adversarial attacks yield outputs …
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems, detecting the presence of adversarial examples is of high practical relevance. By applying anomalous pattern detection techniques in the activation space of these models, we show that 2 of the recent and current state-of-the-art adversarial attacks on audio processing systems systematically lead to higher-than-expected activation at some subset of nodes and we…
The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either require a re-training of a given model to achieve robust identification of adversarial attacks or are limited to out-of-distribution sample detection only. In this work, we propose a geometric gradient analysis (GGA) to improve the identification of untrustworthy predictions without retraining of a given model. GGA analyzes the geometry of the loss landscape of…
We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on clean and adversarial data. Utilizing this intuition, we propose a framework which can identify whether a given input is adversarial based on the explanations given by the model. Code for our experiments can be found here: https://github.com/seansaito/Explaining-Away-Attacks-Against-Neural-Networks.
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then frame commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarial risk. This suggests that models may optimize this surrogate rather than the true adversarial risk. We formalize this notion as 'obscurity to an adversary,' and develop tools and heuristics for identifying obscured models and designing transp…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word or phrase to an input. This paper considers the problem of diagnosing whether a model has been compromised and if so, identifying the backdoor trigger. We present the first robust defence mechanism that generalizes to several backdoor attacks against text classification models, without prior knowledge of the attack type, nor does our method require access to…
An Adversarial System to attack and an Authorship Attribution System (AAS) to defend itself against the attacks are analyzed. Defending a system against attacks from an adversarial machine learner can be done by randomly switching between models for the system, by detecting and reacting to changes in the distribution of normal inputs, or by using other methods. Adversarial machine learning is used to identify a system that is being used to map system inputs to outputs. Three types of machine learners are using for the model that is being attacked. The machine learners that are used to model th…
Edinburgh Napier University（爱丁堡龙比亚大学）；University of Hertfordshire（赫特福德大学）
As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought. Traditional defending approaches are no longer sufficient to detect both known and unknown attacks to high accuracy. Machine learning intrusion detection systems have proven their success in identifying unknown attacks with high precision. Nevertheless, machine learning models are also vulnerable to attacks. Adversarial examples can be used to evaluate the robustn…
Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost method to explore marginal sample data near trained classifier decision boundaries, thus identifying potential adversarial samples. By finding such adversarial samples it is possible to reduce the search space of adversarial attack algorithms while keeping a reasonable successful perturbation rate. In our developed strategy, the potential adversarial samples r…
The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of robustness. Many promising defenses could be broken later on, making it difficult to identify the state-of-the-art. Frequent pitfalls in the evaluation are improper tuning of hyperparameters of the attacks, gradient obfuscation or masking. In this paper we first propose two extensions of the PGD-attack overcoming failures due to suboptimal step size and problems of t…
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the goal of an adversary is to infer distributional information about the training data. So far, research on distribution inference has focused on demonstrating successful attacks, with little attention given to identifying the potential causes of the leakage and to proposing mitigations. To bridge this gap, as our main contribution, we theoreti…
Uppsala University（乌普萨拉大学）；Hamad bin Khalifa University（哈马德·本·哈利法大学）
We present a new machine learning-based attack that exploits network patterns to detect the presence of smart IoT devices and running services in the WiFi radio spectrum. We perform an extensive measurement campaign of data collection, and we build up a model describing the traffic patterns characterizing three popular IoT smart home devices, i.e., Google Nest Mini, Amazon Echo, and Amazon Echo Dot. We prove that it is possible to detect and identify with overwhelming probability their presence and the services running by the aforementioned devices in a crowded WiFi scenario. This work proves …
City University of Hong Kong（香港城市大学）；University of Puerto Rico at Mayagüez（波多黎各大学马亚圭斯分校）；University of Victoria（维多利亚大学）；Tsinghua University（清华大学）
For autonomous driving, an essential task is to detect surrounding objects accurately. To this end, most existing systems use optical devices, including cameras and light detection and ranging (LiDAR) sensors, to collect environment data in real time. In recent years, many researchers have developed advanced machine learning models to detect surrounding objects. Nevertheless, the aforementioned optical devices are vulnerable to optical signal attacks, which could compromise the accuracy of object detection. To address this critical issue, we propose a framework to detect and identify sensors t…
Fuzhou University（福州大学）；East China Normal University（华东师范大学）
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose a novel backdoor defense method to mark and purify the infected neurons in the backdoored neural networks. Specifically, we first define a new metric, called benign salience. By combining the first-order gradient to retain the connections between neurons, benign salience can identify the infected neurons with higher accuracy than the commonly used metric in backdoor defense. Th…
Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks
SBA Research（SBA研究中心）；Vienna University of Technology（维也纳工业大学）
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the important domain of detecting personal attacks in social media comments, we additionally demonstrate the importance of manually setting a semantically appropriate `default' behavior for the model by explicitly manipulating its bias term. We develop a validation set of human-annotated…
Rochester Institute of Technology（罗切斯特理工学院）；Global Cybersecurity Institute（全球网络安全研究所）
Visually similar characters, or homoglyphs, can be used to perform social engineering attacks or to evade spam and plagiarism detectors. It is thus important to understand the capabilities of an attacker to identify homoglyphs -- particularly ones that have not been previously spotted -- and leverage them in attacks. We investigate a deep-learning model using embedding learning, transfer learning, and augmentation to determine the visual similarity of characters and thereby identify potential homoglyphs. Our approach uniquely takes advantage of weak labels that arise from the fact that most ch…
Anomaly detection aims at identifying unexpected fluctuations in the expected behavior of a given system. It is acknowledged as a reliable answer to the identification of zero-day attacks to such extent, several ML algorithms that suit for binary classification have been proposed throughout years. However, the experimental comparison of a wide pool of unsupervised algorithms for anomaly-based intrusion detection against a comprehensive set of attacks datasets was not investigated yet. To fill such gap, we exercise seventeen unsupervised anomaly detection algorithms on eleven attack datasets. R…
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
University of Alberta（阿尔伯塔大学）；Michigan State University（密歇根州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）；DSO National Laboratories（新加坡国防科技局国家实验室）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院MIT-IBM沃森人工智能实验室）
Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning based NER models are increasingly being applied in privacy-sensitive applications that need automatic and scalable identification of sensitive information to redact text for data sharing. In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training dataset…
