Derui Wang

Wanlun Ma, Derui Wang, Ruoxi Sun et al.

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses usually rely on the assumption of the universal backdoor setting in which poisoned samples share the same uniform trigger. However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses. In this work, we propose a novel technique, Beatrix (backdoor detection via Gram matrix). Beatrix utilizes Gram matrix to capture not only the feature correlations but also the appropriately high-order information of the representations. By learning class-conditional statistics from activation patterns of normal samples, Beatrix can identify poisoned samples by capturing the anomalies in activation patterns. To further improve the performance in identifying target labels, Beatrix leverages kernel-based testing without making any prior assumptions on representation distribution. We demonstrate the effectiveness of our method through extensive evaluation and comparison with state-of-the-art defensive techniques. The experimental results show that our approach achieves an F1 score of 91.1% in detecting dynamic backdoors, while the state of the art can only reach 36.9%.

Qi Lv, Ziqiang Cao, Wenrui Xie et al. · tencent-ai

With the tremendously increasing number of videos, there is a great demand for techniques that help people quickly navigate to the video segments they are interested in. However, current works on video understanding mainly focus on video content summarization, while little effort has been made to explore the structure of a video. Inspired by textual outline generation, we introduce a novel video understanding task, namely video outline generation (VOG). This task is defined to contain two sub-tasks: (1) first segmenting the video according to the content structure and then (2) generating a heading for each segment. To learn and evaluate VOG, we annotate a 10k+ dataset, called DuVOG. Specifically, we use OCR tools to recognize subtitles of videos. Then annotators are asked to divide subtitles into chapters and title each chapter. In videos, highlighted text tends to be the headline since it is more likely to attract attention. Therefore we propose a Visual Subtitle feature Enhanced video outline generation model (VSENet) which takes as input the textual subtitles together with their visual font sizes and positions. We consider the VOG task as a sequence tagging problem that extracts spans where the headings are located and then rewrites them to form the final outlines. Furthermore, based on the similarity between video outlines and textual outlines, we use a large number of articles with chapter headings to pretrain our model. Experiments on DuVOG show that our model largely outperforms other baseline methods, achieving 77.1 of F1-score for the video segmentation level and 85.0 of ROUGE-L_F0.5 for the headline generation level.

Huajie Chen, Tianqing Zhu, Lefeng Zhang et al.

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available at https://anonymous.4open.science/r/queen implementation-5408/.

Chunhui Ai, Derui Wang, Xu Yan et al.

With so many articles of varying qualities being produced every moment, it is a very urgent task to screen outstanding articles and commit them to social media. To our best knowledge, there is a lack of datasets and mature research works in identifying high-quality articles. Consequently, we conduct some surveys and finalize 7 objective indicators to annotate the quality of 10k articles. During annotation, we find that many characteristics of high-quality articles (e.g., background) rely more on extensive external knowledge than inner semantic information of articles. In response, we link extracted article entities to Baidu Encyclopedia, then propose Knowledge Enhanced article Quality Identification (KE-QI) dataset. To make better use of external knowledge, we propose a compound model which fuses the text and external knowledge information via a gate unit to classify the quality of an article. Our experimental results on KE-QI show that with initialization of our pre-trained Node2Vec model, our model achieves about 78\% $F_1$, outperforming other baselines.

Yuxin Cao, Yumeng Zhu, Derui Wang et al.

Face recognition pipelines have been widely deployed in various mission-critical systems in trust, equitable and responsible AI applications. However, the emergence of adversarial attacks has threatened the security of the entire recognition pipeline. Despite the sheer number of attack methods proposed for crafting adversarial examples in both digital and physical forms, it is never an easy task to assess the real threat level of different attacks and obtain useful insight into the key risks confronted by face recognition systems. Traditional attacks view imperceptibility as the most important measurement to keep perturbations stealthy, while we suspect that industry professionals may possess a different opinion. In this paper, we delve into measuring the threat brought about by adversarial attacks from the perspectives of the industry and the applications of face recognition. In contrast to widely studied sophisticated attacks in the field, we propose an effective yet easy-to-launch physical adversarial attack, named AdvColor, against black-box face recognition pipelines in the physical world. AdvColor fools models in the recognition pipeline via directly supplying printed photos of human faces to the system under adversarial illuminations. Experimental results show that physical AdvColor examples can achieve a fooling rate of more than 96% against the anti-spoofing model and an overall attack success rate of 88% against the face recognition pipeline. We also conduct a survey on the threats of prevailing adversarial attacks, including AdvColor, to understand the gap between the machine-measured and human-assessed threat levels of different forms of adversarial attacks. The survey results surprisingly indicate that, compared to deliberately launched imperceptible attacks, perceptible but accessible attacks pose more lethal threats to real-world commercial systems of face recognition.

Duoxun Tang, Yuxin Cao, Xi Xiao et al.

Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global color, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three steps. The first step involves building a style references set for logos, which can not only make the generated examples more natural, but also carry more target class features in the targeted attacks. Then, reinforcement learning (RL) is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbation optimization is designed to optimize perturbations to improve the fooling rate in a step-by-step manner. Sufficient experimental results indicate that, SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods.

Yuxin Cao, Yian Li, Yumeng Zhu et al.

Anti-spoofing detection has become a necessity for face recognition systems due to the security threat posed by spoofing attacks. Despite great success in traditional attacks, most deep-learning-based methods perform poorly in 3D masks, which can highly simulate real faces in appearance and structure, suffering generalizability insufficiency while focusing only on the spatial domain with single frame input. This has been mitigated by the recent introduction of a biomedical technology called rPPG (remote photoplethysmography). However, rPPG-based methods are sensitive to noisy interference and require at least one second (> 25 frames) of observation time, which induces high computational overhead. To address these challenges, we propose a novel 3D mask detection framework, called FASTEN (Flow-Attention-based Spatio-Temporal aggrEgation Network). We tailor the network for focusing more on fine-grained details in large movements, which can eliminate redundant spatio-temporal feature interference and quickly capture splicing traces of 3D masks in fewer frames. Our proposed network contains three key modules: 1) a facial optical flow network to obtain non-RGB inter-frame flow information; 2) flow attention to assign different significance to each frame; 3) spatio-temporal aggregation to aggregate high-level spatial features and temporal transition features. Through extensive experiments, FASTEN only requires five frames of input and outperforms eight competitors for both intra-dataset and cross-dataset evaluations in terms of multiple detection metrics. Moreover, FASTEN has been deployed in real-world mobile devices for practical 3D mask detection.

Derui Wang, Kristen Moore, Diksha Goel et al.

Deep reinforcement learning (DRL) has gained widespread adoption in control and decision-making tasks due to its strong performance in dynamic environments. However, DRL agents are vulnerable to noisy observations and adversarial attacks, and concerns about the adversarial robustness of DRL systems have emerged. Recent efforts have focused on addressing these robustness issues by establishing rigorous theoretical guarantees for the returns achieved by DRL agents in adversarial settings. Among these approaches, policy smoothing has proven to be an effective and scalable method for certifying the robustness of DRL agents. Nevertheless, existing certifiably robust DRL relies on policies trained with simple Gaussian augmentations, resulting in a suboptimal trade-off between certified robustness and certified return. To address this issue, we introduce a novel paradigm dubbed \texttt{C}ertified-r\texttt{A}dius-\texttt{M}aximizing \texttt{P}olicy (\texttt{CAMP}) training. \texttt{CAMP} is designed to enhance DRL policies, achieving better utility without compromising provable robustness. By leveraging the insight that the global certified radius can be derived from local certified radii based on training-time statistics, \texttt{CAMP} formulates a surrogate loss related to the local certified radius and optimizes the policy guided by this surrogate loss. We also introduce \textit{policy imitation} as a novel technique to stabilize \texttt{CAMP} training. Experimental results demonstrate that \texttt{CAMP} significantly improves the robustness-return trade-off across various tasks. Based on the results, \texttt{CAMP} can achieve up to twice the certified expected return compared to that of baselines. Our code is available at https://github.com/NeuralSec/camp-robust-rl.

Zhisheng Zhang, Derui Wang, Qianyi Yang et al.

Speech synthesis technology has brought great convenience, while the widespread usage of realistic deepfake audio has triggered hazards. Malicious adversaries may unauthorizedly collect victims' speeches and clone a similar voice for illegal exploitation (\textit{e.g.}, telecom fraud). However, the existing defense methods cannot effectively prevent deepfake exploitation and are vulnerable to robust training techniques. Therefore, a more effective and robust data protection method is urgently needed. In response, we propose a defensive framework, \textit{\textbf{SafeSpeech}}, which protects the users' audio before uploading by embedding imperceptible perturbations on original speeches to prevent high-quality synthetic speech. In SafeSpeech, we devise a robust and universal proactive protection technique, \textbf{S}peech \textbf{PE}rturbative \textbf{C}oncealment (\textbf{SPEC}), that leverages a surrogate model to generate universally applicable perturbation for generative synthetic models. Moreover, we optimize the human perception of embedded perturbation in terms of time and frequency domains. To evaluate our method comprehensively, we conduct extensive experiments across advanced models and datasets, both subjectively and objectively. Our experimental results demonstrate that SafeSpeech achieves state-of-the-art (SOTA) voice protection effectiveness and transferability and is highly robust against advanced adaptive adversaries. Moreover, SafeSpeech has real-time capability in real-world tests. The source code is available at \href{https://github.com/wxzyd123/SafeSpeech}{https://github.com/wxzyd123/SafeSpeech}.

Bingbing Song, Derui Wang, Tianwei Zhang et al.

As an emerging concept, steganography without embedding (SWE) hides a secret message without directly embedding it into a cover. Thus, SWE has the unique advantage of being immune to typical steganalysis methods and can better protect the secret message from being exposed. However, existing SWE methods are generally criticized for their poor payload capacity and low fidelity of recovered secret messages. In this paper, we propose a novel steganography-without-embedding technique, named DF-SWE, which addresses the aforementioned drawbacks and produces diverse and natural stego images. Specifically, DF-SWE employs a reversible circulation of double flow to build a reversible bijective transformation between the secret image and the generated stego image. Hence, it provides a way to directly generate stego images from secret images without a cover image. Besides leveraging the invertible property, DF-SWE can invert a secret image from a generated stego image in a nearly lossless manner and increases the fidelity of extracted secret images. To the best of our knowledge, DF-SWE is the first SWE method that can hide large images and multiple images into one image with the same size, significantly enhancing the payload capacity. According to the experimental results, the payload capacity of DF-SWE achieves 24-72 BPP is 8000-16000 times compared to its competitors while producing diverse images to minimize the exposure risk. Importantly, DF-SWE can be applied in the steganography of secret images in various domains without requiring training data from the corresponding domains. This domain-agnostic property suggests that DF-SWE can 1) be applied to hiding private data and 2) be deployed in resource-limited systems.

Zhisheng Zhang, Qianyi Yang, Derui Wang et al.

With just a few speech samples, it is possible to perfectly replicate a speaker's voice in recent years, while malicious voice exploitation (e.g., telecom fraud for illegal financial gain) has brought huge hazards in our daily lives. Therefore, it is crucial to protect publicly accessible speech data that contains sensitive information, such as personal voiceprints. Most previous defense methods have focused on spoofing speaker verification systems in timbre similarity but the synthesized deepfake speech is still of high quality. In response to the rising hazards, we devise an effective, transferable, and robust proactive protection technology named Pivotal Objective Perturbation (POP) that applies imperceptible error-minimizing noises on original speech samples to prevent them from being effectively learned for text-to-speech (TTS) synthesis models so that high-quality deepfake speeches cannot be generated. We conduct extensive experiments on state-of-the-art (SOTA) TTS models utilizing objective and subjective metrics to comprehensively evaluate our proposed method. The experimental results demonstrate outstanding effectiveness and transferability across various models. Compared to the speech unclarity score of 21.94% from voice synthesizers trained on samples without protection, POP-protected samples significantly increase it to 127.31%. Moreover, our method shows robustness against noise reduction and data augmentation techniques, thereby greatly reducing potential hazards.

Dayong Ye, Tianqing Zhu, Congcong Zhu et al.

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the research of unlearning is reinforcement learning. Reinforcement learning focuses on training an agent to make optimal decisions within an environment to maximize its cumulative rewards. During the training, the agent tends to memorize the features of the environment, which raises a significant concern about privacy. As per data protection regulations, the owner of the environment holds the right to revoke access to the agent's training data, thus necessitating the development of a novel and pressing research field, known as \emph{reinforcement unlearning}. Reinforcement unlearning focuses on revoking entire environments rather than individual data samples. This unique characteristic presents three distinct challenges: 1) how to propose unlearning schemes for environments; 2) how to avoid degrading the agent's performance in remaining environments; and 3) how to evaluate the effectiveness of unlearning. To tackle these challenges, we propose two reinforcement unlearning methods. The first method is based on decremental reinforcement learning, which aims to erase the agent's previously acquired knowledge gradually. The second method leverages environment poisoning attacks, which encourage the agent to learn new, albeit incorrect, knowledge to remove the unlearning environment. Particularly, to tackle the third challenge, we introduce the concept of ``environment inference attack'' to evaluate the unlearning outcomes.

Yuxin Cao, Ziyu Zhao, Xi Xiao et al.

Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used in video attacks recently. In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization. We solve the first challenge by scaling down the perturbation range to a regional logo, while the second challenge is addressed by complementing an optimization stage after reinforcement learning. Experimental results substantiate the overall superiority of LogoStyleFool over three state-of-the-art patch-based attacks in terms of attack performance and semantic preservation. Meanwhile, LogoStyleFool still maintains its performance against two existing patch-based defense methods. We believe that our research is beneficial in increasing the attention of the security community to such subregional style transfer attacks.

Weifei Jin, Yuxin Cao, Junjie Su et al.

The widespread application of automatic speech recognition (ASR) supports large-scale voice surveillance, raising concerns about privacy among users. In this paper, we concentrate on using adversarial examples to mitigate unauthorized disclosure of speech privacy thwarted by potential eavesdroppers in speech communications. While audio adversarial examples have demonstrated the capability to mislead ASR models or evade ASR surveillance, they are typically constructed through time-intensive offline optimization, restricting their practicality in real-time voice communication. Recent work overcame this limitation by generating universal adversarial perturbations (UAPs) and enhancing their transferability for black-box scenarios. However, they introduced excessive noise that significantly degrades audio quality and affects human perception, thereby limiting their effectiveness in practical scenarios. To address this limitation and protect live users' speech against ASR systems, we propose a novel framework, AudioShield. Central to this framework is the concept of Transferable Universal Adversarial Perturbations in the Latent Space (LS-TUAP). By transferring the perturbations to the latent space, the audio quality is preserved to a large extent. Additionally, we propose target feature adaptation to enhance the transferability of UAPs by embedding target text features into the perturbations. Comprehensive evaluation on four commercial ASR APIs (Google, Amazon, iFlytek, and Alibaba), three voice assistants, two LLM-powered ASR and one NN-based ASR demonstrates the protection superiority of AudioShield over existing competitors, and both objective and subjective evaluations indicate that AudioShield significantly improves the audio quality. Moreover, AudioShield also shows high effectiveness in real-time end-to-end scenarios, and demonstrates strong resilience against adaptive countermeasures.

Diksha Goel, Kristen Moore, Mingyu Guo et al.

This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of organizational Active Directory (AD) systems. Unlike the existing literature on edge-blocking defenses which considers AD systems as static entities, our study counters this by recognizing their dynamic nature and developing advanced edge-blocking defenses through a Stackelberg game model between attacker and defender. We devise a Reinforcement Learning (RL)-based attack strategy and an RL-assisted Evolutionary Diversity Optimization-based defense strategy, where the attacker and defender improve each other strategy via parallel gameplay. To address the computational challenges of training attacker-defender strategies on numerous dynamic AD graphs, we propose an RL Training Facilitator that prunes environments and neural networks to eliminate irrelevant elements, enabling efficient and scalable training for large graphs. We extensively train the attacker strategy, as a sophisticated attacker model is essential for a robust defense. Our empirical results successfully demonstrate that our proposed approach enhances defender's proficiency in hardening dynamic AD graphs while ensuring scalability for large-scale AD.

Youwei Shu, Xi Xiao, Derui Wang et al.

Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been achieved in providing defenses against $\ell_p$ adversaries, the interaction between the smoothing distribution and the robustness certification still remains vague. In this work, we comprehensively study the effect of two families of distributions, named Exponential Standard Gaussian (ESG) and Exponential General Gaussian (EGG) distributions, on Randomized Smoothing and Double Sampling Randomized Smoothing (DSRS). We derive an analytic formula for ESG's certified radius, which converges to the origin formula of RS as the dimension $d$ increases. Additionally, we prove that EGG can provide tighter constant factors than DSRS in providing $Ω(\sqrt{d})$ lower bounds of $\ell_2$ certified radius, and thus further addresses the curse of dimensionality in RS. Our experiments on real-world datasets confirm our theoretical analysis of the ESG distributions, that they provide almost the same certification under different exponents $η$ for both RS and DSRS. In addition, EGG brings a significant improvement to the DSRS certification, but the mechanism can be different when the classifier properties are different. Compared to the primitive DSRS, the increase in certified accuracy provided by EGG is prominent, up to 6.4% on ImageNet.

Yuxin Cao, Xi Xiao, Ruoxi Sun et al.

Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational overhead in the process of attack. On the other hand, attacks with restricted perturbations are ineffective against defenses such as denoising or adversarial training. In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system. StyleFool first utilizes color theme proximity to select the best style image, which helps avoid unnatural details in the stylized videos. Meanwhile, the target class confidence is additionally considered in targeted attacks to influence the output distribution of the classifier by moving the stylized video closer to or even across the decision boundary. A gradient-free method is then employed to further optimize the adversarial perturbations. We carry out extensive experiments to evaluate StyleFool on two standard datasets, UCF-101 and HMDB-51. The experimental results demonstrate that StyleFool outperforms the state-of-the-art adversarial attacks in terms of both the number of queries and the robustness against existing defenses. Moreover, 50% of the stylized videos in untargeted attacks do not need any query since they can already fool the video classification model. Furthermore, we evaluate the indistinguishability through a user study to show that the adversarial samples of StyleFool look imperceptible to human eyes, despite unrestricted perturbations.

Yansong Gao, Chang Xu, Derui Wang et al.

A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Trojan attacks exploit an effective backdoor created in a DNN model by leveraging the difficulty in interpretability of the learned model to misclassify any inputs signed with the attacker's chosen trojan trigger. Since the trojan trigger is a secret guarded and exploited by the attacker, detecting such trojan inputs is a challenge, especially at run-time when models are in active operation. This work builds STRong Intentional Perturbation (STRIP) based run-time trojan attack detection system and focuses on vision system. We intentionally perturb the incoming input, for instance by superimposing various image patterns, and observe the randomness of predicted classes for perturbed inputs from a given deployed model---malicious or benign. A low entropy in predicted classes violates the input-dependence property of a benign model and implies the presence of a malicious input---a characteristic of a trojaned input. The high efficacy of our method is validated through case studies on three popular and contrasting datasets: MNIST, CIFAR10 and GTSRB. We achieve an overall false acceptance rate (FAR) of less than 1%, given a preset false rejection rate (FRR) of 1%, for different types of triggers. Using CIFAR10 and GTSRB, we have empirically achieved result of 0% for both FRR and FAR. We have also evaluated STRIP robustness against a number of trojan attack variants and adaptive attacks.

Derui Wang, Chaoran Li, Sheng Wen et al.

This paper demonstrates that Non-Maximum Suppression (NMS), which is commonly used in Object Detection (OD) tasks to filter redundant detection results, is no longer secure. Considering that NMS has been an integral part of OD systems, thwarting the functionality of NMS can result in unexpected or even lethal consequences for such systems. In this paper, an adversarial example attack which triggers malfunctioning of NMS in end-to-end OD models is proposed. The attack, namely \texttt{Daedalus}, compresses the dimensions of detection boxes to evade NMS. As a result, the final detection output contains extremely dense false positives. This can be fatal for many OD applications such as autonomous vehicles and surveillance systems. The attack can be generalised to different end-to-end OD models, such that the attack cripples various OD applications. Furthermore, a way to craft robust adversarial examples is developed by using an ensemble of popular detection models as the substitutes. Considering the pervasive nature of model reusing in real-world OD scenarios, Daedalus examples crafted based on an \textit{ensemble of substitutes} can launch attacks without knowing the parameters of the victim models. Experimental results demonstrate that the attack effectively stops NMS from filtering redundant bounding boxes. As the evaluation results suggest, Daedalus increases the false positive rate in detection results to $99.9\%$ and reduces the mean average precision scores to $0$, while maintaining a low cost of distortion on the original inputs. It is also demonstrated that the attack can be practically launched against real-world OD systems via printed posters.

Xiao Chen, Chaoran Li, Derui Wang et al.

Machine learning based solutions have been successfully employed for automatic detection of malware on Android. However, machine learning models lack robustness to adversarial examples, which are crafted by adding carefully chosen perturbations to the normal inputs. So far, the adversarial examples can only deceive detectors that rely on syntactic features (e.g., requested permissions, API calls, etc), and the perturbations can only be implemented by simply modifying application's manifest. While recent Android malware detectors rely more on semantic features from Dalvik bytecode rather than manifest, existing attacking/defending methods are no longer effective. In this paper, we introduce a new attacking method that generates adversarial examples of Android malware and evades being detected by the current models. To this end, we propose a method of applying optimal perturbations onto Android APK that can successfully deceive the machine learning detectors. We develop an automated tool to generate the adversarial examples without human intervention. In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning based detectors that rely on semantic features such as control-flow-graph. The perturbations can also be implemented directly onto APK's Dalvik bytecode rather than Android manifest to evade from recent detectors. We demonstrate our attack on two state-of-the-art Android malware detection schemes, MaMaDroid and Drebin. Our results show that the malware detection rates decreased from 96% to 0% in MaMaDroid, and from 97% to 0% in Drebin, with just a small number of codes to be inserted into the APK.