Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the predictions of DNNs by adding a universal adversarial perturbation (UAP) to benign samples. On the other hand, increasing efforts have been made to help users understand and explain the inner working of DNNs by highlighting the most informative parts (i.e., attribution maps) of samples with respect to their predictions. Moreover, we first empirically find that such attribution maps between benign and adversarial examples have a significant discrepancy, which has the potential to detect universal adversarial perturbations for defending against adversarial attacks. This finding motivates us to further investigate a new research problem: whether there exist universal adversarial perturbations that are able to jointly attack DNNs classifier and its interpretation with malicious desires. It is challenging to give an explicit answer since these two objectives are seemingly conflicting. In this paper, we propose a novel attacking framework to generate joint universal adversarial perturbations (JUAP), which can fool the DNNs model and misguide the inspection from interpreters simultaneously. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed method JUAP for joint attacks. To the best of our knowledge, this is the first effort to study UAP for jointly attacking both DNNs and interpretations.
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Department of Computer Science and Engineering, Sungkyunkwan University（计算机科学与工程系，全州大学）；Department of Computer Science, Loyola University（计算机科学系，洛伊拉大学）
The Center for Brains, Minds and Machines（大脑、心智与机器中心）；Massachusetts Institute of Technology（麻省理工学院）
Modern high-scoring models of vision in the brain score competition do not stem from Vision Transformers. However, in this paper, we provide evidence against the unexpected trend of Vision Transformers (ViT) being not perceptually aligned with human visual representations by showing how a dual-stream Transformer, a CrossViT$~\textit{a la}$ Chen et al. (2021), under a joint rotationally-invariant and adversarial optimization procedure yields 2nd place in the aggregate Brain-Score 2022 competition(Schrimpf et al., 2020b) averaged across all visual categories, and at the time of the competition h…
We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image generation by jointly optimizing discriminator and generator. We show these two concepts are indeed closely related and can be used to strengthen each other---adding a generator to the adversarial training procedure can improve the robustness of discriminators, and adding an advers…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of two aspects: i) how to extract accurate rationales for explainability while being beneficial to prediction; ii) how to make the predictive model robust to different types of adversarial attacks. Intuitively, a model that produces helpful explanations should be more robust against adversarial attacks, because we cannot trust the model that outputs explanations but changes its prediction under small perturbations. To thi…
Center for Language and Speech Processing, Johns Hopkins University（约翰霍普金斯大学语言与语音处理中心）
Adversarial attacks are a threat to automatic speech recognition (ASR) systems, and it becomes imperative to propose defenses to protect them. In this paper, we perform experiments to show that K2 conformer hybrid ASR is strongly affected by white-box adversarial attacks. We propose three defenses--denoiser pre-processor, adversarially fine-tuning ASR model, and adversarially fine-tuning joint model of ASR and denoiser. Our evaluation shows denoiser pre-processor (trained on offline adversarial examples) fails to defend against adaptive white-box attacks. However, adversarially fine-tuning the…
Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given task, interpretation models have become a crucial component in developing deep learning-based systems. Interpretation models enable the understanding of the inner workings of deep learning models and offer a sense of security in detecting the misuse of artifacts in the input data. Similar to prediction models, interpretation models are also susceptib…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；TTIC（丰田工业大学芝加哥分校）
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initializ…
Adversarial images are created with the intention of causing an image classifier to produce a misclassification. In this paper, we propose that adversarial images should be evaluated based on semantic mismatch, rather than label mismatch, as used in current work. In other words, we propose that an image of a "mug" would be considered adversarial if classified as "turnip", but not as "cup", as current systems would assume. Our novel idea of taking semantic misclassification into account in the evaluation of adversarial images offers two benefits. First, it is a more realistic conceptualization …
Georgia Institute of Technology（佐治亚理工学院）；GTRI（佐治亚技术研究所）
Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such applications. Recent research has also revealed that DNNs are highly vulnerable to adversarial attacks, raising serious concerns over deploying DNNs in the real world. To overcome these deficiencies, we are developing Massif, an interactive tool for deciphering adversarial attacks. Massif identifies and interactively visualizes neurons and their connections inside a DNN that are strongly activated or suppressed by an adv…
Deep Neural Networks (DNNs) are often vulnerable to adversarial examples.Several proposed defenses deploy an ensemble of models with the hope that, although the individual models may be vulnerable, an adversary will not be able to find an adversarial example that succeeds against the ensemble. Depending on how the ensemble is used, an attacker may need to find a single adversarial example that succeeds against all, or a majority, of the models in the ensemble. The effectiveness of ensemble defenses against strong adversaries depends on the vulnerability spaces of models in the ensemble being d…
Airbus Defence & Space Cybersecurity（空客防务与航天网络安全部门）
Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security consisting in the detection of hostile action based on the unusual nature of events observed on the Information System.In our previous work (presented at C\&ESAR 2018 and FIC 2019), we have associated deep neural networks auto-encoders for anomaly detection and graph-based events correlation to address major limitations in UEBA systems. This resulted in reduced false positive and false negative rates, improved alert explainability, while maintaining real-time perf…
Pennsylvania State University（宾夕法尼亚州立大学）；University of California Irvine（加州大学欧文分校）；Zhejiang University（浙江大学）；Alibaba-ZJU Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；Hong Kong Polytechnic University（香港理工大学）
Providing explanations for deep neural network (DNN) models is crucial for their use in security-sensitive domains. A plethora of interpretation models have been proposed to help users understand the inner workings of DNNs: how does a DNN arrive at a specific decision for a given input? The improved interpretability is believed to offer a sense of security by involving human in the decision-making process. Yet, due to its data-driven nature, the interpretability itself is potentially susceptible to malicious manipulations, about which little is known thus far. Here we bridge this gap by conduc…
Stevens Institute of Technology（史蒂文斯理工学院）；Nokia Bell Labs（诺基亚贝尔实验室）
Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly sensitive to small perturbations imperceptible to humans. Carefully crafted input images (adversarial examples) can force a well-trained neural network to provide arbitrary outputs. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. In this paper we propose a new defensive mechanism under the generativ…
Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical adversarial example detection methods have proven to be effective defense mechanisms, additional research is necessary that investigates the fundamental vulnerabilities of deep-learning-based systems and how best to build models that jointly maximize traditional and robust accuracy. This paper presents the inclusion of attention mechanisms in CNN-based medical …
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tencent AI Lab（腾讯人工智能实验室）
Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which encourages both the benign example $x$ and its adversarially perturbed neighborhoods within the $\ell_{p}$-ball to be predicted as the ground-truth label. In this work, we propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_{stand}$ and $R_{rob}$), which is with respect to the benign example and its neighborhoods …
