Debdeep Mukhopadhyay

Manaar Alam, Shubhajit Datta, Debdeep Mukhopadhyay et al.

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify. Protections against adversarial perturbations on ensemble-based techniques have either been shown to be vulnerable to stronger adversaries or shown to lack an end-to-end evaluation. In this paper, we attempt to develop a new ensemble-based solution that constructs defender models with diverse decision boundaries with respect to the original model. The ensemble of classifiers constructed by (1) transformation of the input by a method called Split-and-Shuffle, and (2) restricting the significant features by a method called Contrast-Significant-Features are shown to result in diverse gradients with respect to adversarial attacks, which reduces the chance of transferring adversarial examples from the original to the defender model targeting the same class. We present extensive experimentations using standard image classification datasets, namely MNIST, CIFAR-10 and CIFAR-100 against state-of-the-art adversarial attacks to demonstrate the robustness of the proposed ensemble-based defense. We also evaluate the robustness in the presence of a stronger adversary targeting all the models within the ensemble simultaneously. Results for the overall false positives and false negatives have been furnished to estimate the overall performance of the proposed methodology.

Shubhi Shukla, Manaar Alam, Sarani Bhattacharya et al.

Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on privacy-sensitive data for training in a variety of applications, making them an overly-exposed threat surface for privacy violations. Furthermore, the widespread use of cloud-based Machine-Learning-as-a-Service (MLaaS) for its robust infrastructure support has broadened the threat surface to include a variety of remote side-channel attacks. In this paper, we first identify and report a novel data-dependent timing side-channel leakage (termed Class Leakage) in DL implementations originating from non-constant time branching operation in a widely used DL framework PyTorch. We further demonstrate a practical inference-time attack where an adversary with user privilege and hard-label black-box access to an MLaaS can exploit Class Leakage to compromise the privacy of MLaaS users. DL models are vulnerable to Membership Inference Attack (MIA), where an adversary's objective is to deduce whether any particular data has been used while training the model. In this paper, as a separate case study, we demonstrate that a DL model secured with differential privacy (a popular countermeasure against MIA) is still vulnerable to MIA against an adversary exploiting Class Leakage. We develop an easy-to-implement countermeasure by making a constant-time branching operation that alleviates the Class Leakage and also aids in mitigating MIA. We have chosen two standard benchmarking image classification datasets, CIFAR-10 and CIFAR-100 to train five state-of-the-art pre-trained DL models, over two different computing environments having Intel Xeon and Intel i7 processors to validate our approach.

Shubhi Shukla, Manaar Alam, Pabitra Mitra et al.

Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily available to the public, is fine-tuned to suit specific tasks. As Machine Learning as a Service (MLaaS) platforms increasingly use pre-trained models in their backends, it's crucial to safeguard these architectures and understand their vulnerabilities. In this work, we present an approach based on the observation that the classification patterns of adversarial images can be used as a means to steal the models. Furthermore, the adversarial image classifications in conjunction with timing side channels can lead to a model stealing method. Our approach, designed for typical user-level access in remote MLaaS environments exploits varying misclassifications of adversarial images across different models to fingerprint several renowned Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures. We utilize the profiling of remote model inference times to reduce the necessary adversarial images, subsequently decreasing the number of queries required. We have presented our results over 27 pre-trained models of different CNN and ViT architectures using CIFAR-10 dataset and demonstrate a high accuracy of 88.8% while keeping the query budget under 20.

Shubhi Shukla, Subhadeep Dalui, Manaar Alam et al.

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy ($ε$ = 0.07) from the state-of-the art method.

Manaar Alam, Sayandeep Saha, Debdeep Mukhopadhyay et al.

Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models. Prevention of IP theft and unauthorized usage of such DNN models has been raised as of significant concern by industry. In this paper, we address the problem of preventing unauthorized usage of DNN models by proposing a generic and lightweight key-based model-locking scheme, which ensures that a locked model functions correctly only upon applying the correct secret key. The proposed scheme, known as Deep-Lock, utilizes S-Boxes with good security properties to encrypt each parameter of a trained DNN model with secret keys generated from a master key via a key scheduling algorithm. The resulting dense network of encrypted weights is found robust against model fine-tuning attacks. Finally, Deep-Lock does not require any intervention in the structure and training of the DNN models, making it applicable for all existing software and hardware implementations of DNN.

Sunandan Adhikary, Ipsita Koley, Sumana Ghosh et al.

We consider the problem of provably securing a given control loop implementation in the presence of adversarial interventions on data exchange between plant and controller. Such interventions can be thwarted using continuously operating monitoring systems and also cryptographic techniques, both of which consume network and computational resources. We provide a principled approach for intentional skipping of control loop executions which may qualify as a useful control theoretic countermeasure against stealthy attacks which violate message integrity and authenticity. As is evident from our experiments, such a control theoretic counter-measure helps in lowering the cryptographic security measure overhead and resulting resource consumption in Control Area Network (CAN) based automotive CPS without compromising performance and safety.

Manaar Alam, Sayan Sinha, Sarani Bhattacharya et al.

Ransomware can produce direct and controllable economic loss, which makes it one of the most prominent threats in cyber security. As per the latest statistics, more than half of malwares reported in Q1 of 2017 are ransomwares and there is a potent threat of a novice cybercriminals accessing ransomware-as-a-service. The concept of public-key based data kidnapping and subsequent extortion was introduced in 1996. Since then, variants of ransomware emerged with different cryptosystems and larger key sizes, the underlying techniques remained same. Though there are works in literature which proposes a generic framework to detect the crypto ransomwares, we present a two step unsupervised detection tool which when suspects a process activity to be malicious, issues an alarm for further analysis to be carried in the second step and detects it with minimal traces. The two step detection framework- RAPPER uses Artificial Neural Network and Fast Fourier Transformation to develop a highly accurate, fast and reliable solution to ransomware detection using minimal trace points. We also introduce a special detection module for successful identification of disk encryption processes from potential ransomware operations, both having similar characteristics but with different objective. We provide a comprehensive solution to tackle almost all scenarios (standard benchmark, disk encryption and regular high computational processes) pertaining to the crypto ransomwares in light of software security.

Ipsita Koley, Saurav Kumar Ghosh, Soumyajit Dey et al.

We consider the problem of securing a given control loop implementation of a cyber-physical system (CPS) in the presence of Man-in-the-Middle attacks on data exchange between plant and controller over a compromised network. To this end, there exist various detection schemes that provide mathematical guarantees against such attacks for the theoretical control model. However, such guarantees may not hold for the actual control software implementation. In this article, we propose a formal approach towards synthesizing attack detectors with varying thresholds which can prevent performance degrading stealthy attacks while minimizing false alarms.

Johann Knechtel, Elif Bilge Kavun, Francesco Regazzoni et al.

Modern electronic systems become evermore complex, yet remain modular, with integrated circuits (ICs) acting as versatile hardware components at their heart. Electronic design automation (EDA) for ICs has focused traditionally on power, performance, and area. However, given the rise of hardware-centric security threats, we believe that EDA must also adopt related notions like secure by design and secure composition of hardware. Despite various promising studies, we argue that some aspects still require more efforts, for example: effective means for compilation of assumptions and constraints for security schemes, all the way from the system level down to the "bare metal"; modeling, evaluation, and consideration of security-relevant metrics; or automated and holistic synthesis of various countermeasures, without inducing negative cross-effects. In this paper, we first introduce hardware security for the EDA community. Next we review prior (academic) art for EDA-driven security evaluation and implementation of countermeasures. We then discuss strategies and challenges for advancing research and development toward secure composition of circuits and systems.

Anirban Chakraborty, Sarani Bhattacharya, Sayandeep Saha et al.

Page Frame Cache (PFC) is a purely software cache, present in modern Linux based operating systems (OS), which stores the page frames that are recently being released by the processes running on a particular CPU. In this paper, we show that the page frame cache can be maliciously exploited by an adversary to steer the pages of a victim process to some pre-decided attacker-chosen locations in the memory. We practically demonstrate an end-to-end attack, ExplFrame, where an attacker having only user-level privilege is able to force a victim process's memory pages to vulnerable locations in DRAM and deterministically conduct Rowhammer to induce faults. We further show that these faults can be exploited for extracting the secret key of table-based block cipher implementations. As a case study, we perform a full-key recovery on OpenSSL AES by Rowhammer-induced single bit faults in the T-tables. We propose an improvised fault analysis technique which can exploit any Rowhammer-induced bit-flips in the AES T-tables.

Manaar Alam, Arnab Bag, Debapriya Basu Roy et al.

Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs can lead to severe consequences in applications like cryptography and security critical scenarios. In this paper, we propose a revised implementation which enhances the PFT property of NN significantly with detailed mathematical analysis. We evaluated the performance of revised NN considering both software and FPGA implementation for a cryptographic primitive like AES SBox. The results show that the PFT of NNs can be significantly increased with the proposed methodology.

Nimesh Shah, Manaar Alam, Durga Prasad Sahoo et al.

Physically Unclonable Function (PUF) circuits are finding widespread use due to increasing adoption of IoT devices. However, the existing strong PUFs such as Arbiter PUFs (APUF) and its compositions are susceptible to machine learning (ML) attacks because the challenge-response pairs have a linear relationship. In this paper, we present a Recurrent-Neural-Network PUF (RNN-PUF) which uses a combination of feedback and XOR function to significantly improve resistance to ML attack, without significant reduction in the reliability. ML attack is also partly reduced by using a shared comparator with offset-cancellation to remove bias and save power. From simulation results, we obtain ML attack accuracy of 62% for different ML algorithms, while reliability stays above 93%. This represents a 33.5% improvement in our Figure-of-Merit. Power consumption is estimated to be 12.3uW with energy/bit of ~ 0.16pJ.

Manaar Alam, Debdeep Mukhopadhyay

Deep Learning algorithms have recently become the de-facto paradigm for various prediction problems, which include many privacy-preserving applications like online medical image analysis. Presumably, the privacy of data in a deep learning system is a serious concern. There have been several efforts to analyze and exploit the information leakages from deep learning architectures to compromise data privacy. In this paper, however, we attempt to provide an evaluation strategy for such information leakages through deep neural network architectures by considering a case study on Convolutional Neural Network (CNN) based image classifier. The approach takes the aid of low-level hardware information, provided by Hardware Performance Counters (HPCs), during the execution of a CNN classifier and a simple hypothesis testing in order to produce an alarm if there exists any information leakage on the actual input.

Durba Chatterjee, Aritra Hazra, Debdeep Mukhopadhyay

Testability of digital ICs rely on the principle of controllability and observability. Adopting conventional techniques like scan-chains open up avenues for attacks, and hence cannot be adopted in a straight-forward manner for security chips. Furthermore, testing becomes incredibly challenging for the promising class of hardware security primitives, called PUFs, which offer unique properties like unclonability, unpredictibility, uniformity, uniqueness, and yet easily computable. However, the definition of PUF itself poses a challenge on test engineers, simply because it has no golden response for a given input, often called challenge. In this paper, we develop a novel test strategy considering that the fabrication of a batch of $N>1$ PUFs is equivalent to drawing random instances of Boolean mappings. We hence model the PUFs as black-box Boolean functions of dimension $m\times1$, and show combinatorially that random designs of such functions exhibit correlation-spectra which can be used to characterize random and thus {\em good} designs of PUFs. We first develop theoretical results to quantize the correlation values, and subsequently the expected number of pairs of such Boolean functions which should belong to a given spectra. In addition to this, we show through extensive experimental results that a randomly chosen sample of such PUFs also resemble the correlation-spectra property of the overall PUF population. Interestingly, we show through experimental results on $50$ FPGAs that when the PUFs are infected by faults the usual randomness tests for the PUF outputs such as uniformity, fail to detect any aberration. However, the spectral-pattern is clearly shown to get affected, which we demonstrate by standard statistical tools. We finally propose a systematic testing framework for the evaluation of PUFs by observing the correlation-spectra of the PUF instances under test.

Anirban Chakraborty, Manaar Alam, Vishal Dey et al.

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few years, deep learning has advanced radically in such a way that it can surpass human-level performance on a number of tasks. As a consequence, deep learning is being extensively used in most of the recent day-to-day applications. However, security of deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify the output. In recent times, different types of adversaries based on their threat model leverage these vulnerabilities to compromise a deep learning system where adversaries have high incentives. Hence, it is extremely important to provide robustness to deep learning algorithms against these adversaries. However, there are only a few strong countermeasures which can be used in all types of attack scenarios to design a robust deep learning system. In this paper, we attempt to provide a detailed discussion on different types of adversarial attacks with various threat models and also elaborate the efficiency and challenges of recent countermeasures against them.

Arnab Bag, Sikhar Patranabis, Debapriya Basu Roy et al.

FPGAs (Field Programmable Gate arrays) have gained massive popularity today as accelerators for a variety of workloads, including big data analytics, and parallel and distributed computing. This has fueled the study of mechanisms to provision FPGAs among multiple tenants as general purpose computing resources on the cloud. Such mechanisms offer new challenges, such as ensuring IP protection and bitstream confidentiality for mutually distrusting clients sharing the same FPGA. A direct adoption of existing IP protection techniques from the single tenancy setting do not completely address these challenges, and are also not scalable enough for practical deployment. In this paper, we propose a dedicated and scalable framework for secure multi-tenant FPGA provisioning that can be easily integrated into existing cloud-based infrastructures such as OpenStack. Our technique has constant resource/memory overhead irrespective of the number of tenants sharing a given FPGA, and is provably secure under well-studied cryptographic assumptions. A prototype implementation of our proposition on Xilinx Virtex-7 UltraScale FPGAs is presented to validate its overheads and scalability when supporting multiple tenants and workloads. To the best of our knowledge, this is the first FPGA provisioning framework to be prototyped that achieves a desirable balance between security and scalability in the multi-tenancy setting.

Manaar Alam, Sarani Bhattacharya, Debdeep Mukhopadhyay et al.

Ransomware can produce direct and controllable economic loss, which makes it one of the most prominent threats in cyber security. As per the latest statistics, more than half of malwares reported in Q1 of 2017 are ransomware and there is a potent threat of a novice cybercriminals accessing rasomware-as-a-service. The concept of public-key based data kidnapping and subsequent extortion was introduced in 1996. Since then, variants of ransomware emerged with different cryptosystems and larger key sizes though, the underlying techniques remained same. Though there are works in literature which proposes a generic framework to detect the crypto ransomwares, we present a two step unsupervised detection tool which when suspects a process activity to be malicious, issues an alarm for further analysis to be carried in the second step and detects it with minimal traces. The two step detection framework- RAPPER uses Artificial Neural Network and Fast Fourier Transformation to develop a highly accurate, fast and reliable solution to ransomware detection using minimal trace points.