Deep learning-based facial recognition systems have experienced increased media attention due to exhibiting unfair behavior. Large enterprises, such as IBM, shut down their facial recognition and age prediction systems as a consequence. Age prediction is an especially difficult application with the issue of fairness remaining an open research problem (e.g., predicting age for different ethnicity equally accurate). One of the main causes of unfair behavior in age prediction methods lies in the distribution and diversity of the training data. In this work, we present two novel approaches for dataset curation and data augmentation in order to increase fairness through balanced feature curation and increase diversity through distribution aware augmentation. To achieve this, we introduce out-of-distribution detection to the facial recognition domain which is used to select the data most relevant to the deep neural network’s (DNN) task when balancing the data among age, ethnicity, and gender. Our approach shows promising results. Our best-trained DNN model outperformed all academic and industrial baselines in terms of fairness by up to 4.92 times and also enhanced the DNN’s ability to generalize outperforming Amazon AWS and Microsoft Azure public cloud systems by 31.88% and 10.95%, respectively.

Network intrusion attacks are a known threat. To detect such attacks, network intrusion detection systems (NIDSs) have been developed and deployed. These systems apply machine learning models to high-dimensional vectors of features extracted from network traffic to detect intrusions. Advances in NIDSs have made it challenging for attackers, who must execute attacks without being detected by these systems. Prior research on bypassing NIDSs has mainly focused on perturbing the features extracted from the attack traffic to fool the detection system, however, this may jeopardize the attack’s functionality. In this work, we present TANTRA, a novel end-to-end Timing-based Adversarial Network Traffic Reshaping Attack that can bypass a variety of NIDSs. Our evasion attack utilizes a long short-term memory (LSTM) deep neural network (DNN) which is trained to learn the time differences between the target network’s benign packets. The trained LSTM is used to set the time differences between the malicious traffic packets (attack), without changing their content, such that they will “behave” like benign network traffic and will not be detected as an intrusion. We evaluate TANTRA on eight common intrusion attacks and three state-of-the-art NIDS systems, achieving an average success rate of 99.99% in network intrusion detection system evasion. We also propose a novel mitigation technique to address this new evasion attack.

The state-of-the-art deep neural network (DNN) achieves impressive performance on the input that is similar to training data. However, it fails to make reasonable decisions on the input that is quite different from training data, i.e., out-of-distribution (OOD) examples. Although many techniques have been proposed to detect OOD examples in recent years, it is still a lack of a systematic study about the effectiveness and robustness of different techniques as well as the performance of OOD-aware DNN models. In this paper, we conduct a comprehensive study to unveil the mystery of current OOD detection techniques, and investigate the differences between OOD-unaware/-aware DNNs in model performance, robustness, and uncertainty. We first compare the effectiveness of existing detection techniques and identify the best one. Then, evasion attacks are performed to evaluate the robustness of techniques. Furthermore, we compare the accuracy and robustness between OOD-unaware/-aware DNNs. At last, we study the uncertainty of different models on various kinds of data. Empirical results show OOD-aware detection modules have better performance and are more robust against random noises and evasion attacks. OOD-awareness seldom degrades the accuracy of DNN models in training/test datasets. In contrast, it makes the DNN model more robust against adversarial attacks and noisy inputs. Our study calls for attention to the development of OOD-aware DNN models and the necessity to take data distribution into account when robust and reliable DNN models are desired.

As Deep Learning (DL) is continuously adopted in many industrial applications, its quality and reliability start to raise concerns. Similar to the traditional software development process, testing the DL software to uncover its defects at an early stage is an effective way to reduce risks after deployment. According to the fundamental assumption of deep learning, the DL software does not provide statistical guarantee and has limited capability in handling data that falls outside of its learned distribution, i.e., out-of-distribution (OOD) data. Although recent progress has been made in designing novel testing techniques for DL software, which can detect thousands of errors, the current state-of-the-art DL testing techniques usually do not take the distribution of generated test data into consideration. It is therefore hard to judge whether the "identified errors" are indeed meaningful errors to the DL application (i.e., due to quality issues of the model) or outliers that cannot be handled by the current model (i.e., due to the lack of training data). Tofill this gap, we take the first step and conduct a large scale empirical study, with a total of 451 experiment configurations, 42 deep neural networks (DNNs) and 1.2 million test data instances, to investigate and characterize the impact of OOD-awareness on DL testing. We further analyze the consequences when DL systems go into production by evaluating the effectiveness of adversarial retraining with distribution-aware errors. The results confirm that introducing data distribution awareness in both testing and enhancement phases outperforms distribution unaware retraining by up to 21.5%.

A range of zero-permission sensors are found in modern smart-phones to enhance user experience. These sensors can lead to unintentional leakage of user private data. In this paper, we combine leakage from a pool of zero-permission sensors, to reconstruct user's secret PIN used for unlocking the phone or personal finances. By harvesting the power of machine learning algorithms, we show a practical attack on the full four-digit PIN space. Able to classify all 10,000 PIN combinations, results show up to 83.7% success within 20 tries in a single user setting. Latest previous work demonstrated 74% success on a reduced space of 50 chosen PINs, where we report 99.5% success with a single try in a similar setting. Moreover, we extend the PIN recovery attack from a single user to a cross-user scenario. Firstly, we show that by training on several users, the PIN recovery success can be boosted, when a target user is part of the training pool. On the other hand, PIN recovery is still possible when training pool is mutually exclusive to the target user, albeit with low success rate.