arXiv subjects

Yansong Gao

Publications and source records attributed to Yansong Gao.

At least 91 records · Page 5Linked to original sources

arXiv2020

Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures, and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor.Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks. In some cases, an attacker can intelligently bypass existing defenses with an adaptive attack. Drawing the insights from the systematic review, we also present key areas for future research on the backdoor, such as empirical security evaluations from physical trigger attacks, and in particular, more efficient and practical countermeasures are solicited.

cs.CR↗

arXiv2020

VFL: A Verifiable Federated Learning with Privacy-Preserving for Big Data in Industrial IoT

Due to the strong analytical ability of big data, deep learning has been widely applied to train the collected data in industrial IoT. However, for privacy issues, traditional data-gathering centralized learning is not applicable to industrial scenarios sensitive to training sets. Recently, federated learning has received widespread attention, since it trains a model by only relying on gradient aggregation without accessing training sets. But existing researches reveal that the shared gradient still retains the sensitive information of the training set. Even worse, a malicious aggregation server may return forged aggregated gradients. In this paper, we propose the VFL, verifiable federated learning with privacy-preserving for big data in industrial IoT. Specifically, we use Lagrange interpolation to elaborately set interpolation points for verifying the correctness of the aggregated gradients. Compared with existing schemes, the verification overhead of VFL remains constant regardless of the number of participants. Moreover, we employ the blinding technology to protect the privacy of the gradients submitted by the participants. If no more than n-2 of n participants collude with the aggregation server, VFL could guarantee the encrypted gradients of other participants not being inverted. Experimental evaluations corroborate the practical performance of the presented VFL framework with high accuracy and efficiency.

cs.CR↗

arXiv2020

A Channel Perceiving Attack on Long-Range Key Generation and Its Countermeasure

The physical-layer key generation is a lightweight technique to generate secret keys from wireless channels for resource-constrained Internet of things (IoT) applications. The security of key generation relies on spatial decorrelation, which assumes that eavesdroppers observe uncorrelated channel measurements when they are located over a half-wavelength away from legitimate users. Unfortunately, there is no experimental validation for communications environments when there are large-scale and small-scale fading effects. Furthermore, while the current key generation work mainly focuses on short-range communications techniques such as WiFi and ZigBee, the exploration with long-range communications, e.g., LoRa, is rather limited. This paper presents a LoRa-based key generation testbed and reveals a new colluding-eavesdropping attack that perceives and utilizes large-scale fading effects in key generation channels, by using multiple eavesdroppers circularly around a legitimate user. We formalized the attack and validated it through extensive experiments conducted under both indoor and outdoor environments. It is corroborated that the attack reduces secret key capacity when large-scale fading is predominant. We further investigated potential defenses by proposing a conditional entropy and high-pass filter-based countermeasure to estimate and eliminate large-scale fading associated components. The experimental results demonstrated that the countermeasure can significantly improve the key generation's security when there are both varying large-scale and small-scale fading effects. The key bits generated by legitimate users have a low key disagreement rate (KDR) and validated by the NIST randomness tests. On the other hand, eavesdroppers' average KDR is increased to 0.49, which is no better than a random guess.

eess.SP↗

arXiv2020

TREVERSE: Trial-and-Error Lightweight Secure Reverse Authentication with Simulatable PUFs

A physical unclonable function (PUF) generates hardware intrinsic volatile secrets by exploiting uncontrollable manufacturing randomness. Although PUFs provide the potential for lightweight and secure authentication for increasing numbers of low-end Internet of Things devices, practical and secure mechanisms remain elusive. We aim to explore simulatable PUFs (SimPUFs) that are physically unclonable but efficiently modeled mathematically through privileged one-time PUF access to address the above problem. Given a challenge, a securely stored SimPUF in possession of a trusted server computes the corresponding response and its bit-specific reliability. Consequently, naturally noisy PUF responses generated by a resource limited prover can be immediately processed by a one-way function (OWF) and transmitted to the server, because the resourceful server can exploit the SimPUF to perform a trial-and-error search over likely error patterns to recover the noisy response to authenticate the prover. Security of trial-and-error reverse (TREVERSE) authentication under the random oracle model is guaranteed by the hardness of inverting the OWF. We formally evaluate the TREVERSE authentication capability with two SimPUFs experimentally derived from popular silicon PUFs.

cs.CR↗

arXiv2020

Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?

A new collaborative learning, called split learning, was recently introduced, aiming to protect user data privacy without revealing raw input data to a server. It collaboratively runs a deep neural network model where the model is split into two parts, one for the client and the other for the server. Therefore, the server has no direct access to raw data processed at the client. Until now, the split learning is believed to be a promising approach to protect the client's raw data; for example, the client's data was protected in healthcare image applications using 2D convolutional neural network (CNN) models. However, it is still unclear whether the split learning can be applied to other deep learning models, in particular, 1D CNN. In this paper, we examine whether split learning can be used to perform privacy-preserving training for 1D CNN models. To answer this, we first design and implement an 1D CNN model under split learning and validate its efficacy in detecting heart abnormalities using medical ECG data. We observed that the 1D CNN model under split learning can achieve the same accuracy of 98.9\% like the original (non-split) model. However, our evaluation demonstrates that split learning may fail to protect the raw data privacy on 1D CNN models. To address the observed privacy leakage in split learning, we adopt two privacy leakage mitigation techniques: 1) adding more hidden layers to the client side and 2) applying differential privacy. Although those mitigation techniques are helpful in reducing privacy leakage, they have a significant impact on model accuracy. Hence, based on those results, we conclude that split learning alone would not be sufficient to maintain the confidentiality of raw sequential data in 1D CNN models.

cs.CR↗

arXiv2020

A Free-Energy Principle for Representation Learning

This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learnt representations for transfer learning. We discuss how information-theoretic functional such as rate, distortion and classification loss of a model lie on a convex, so-called equilibrium surface.We prescribe dynamical processes to traverse this surface under constraints, e.g., an iso-classification process that trades off rate and distortion to keep the classification loss unchanged. We demonstrate how this process can be used for transferring representations from a source dataset to a target dataset while keeping the classification loss constant. Experimental validation of the theoretical results is provided on standard image-classification datasets.

cs.LG↗

arXiv2020

STRIP: A Defence Against Trojan Attacks on Deep Neural Networks

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.

cs.CR↗

arXiv2019

Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks

This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically, STRIP-ViTA is the first confirmed Trojan detection method that is demonstratively independent of both the task domain and model architectures. We have extensively evaluated the performance of STRIP-ViTA over: i) CIFAR10 and GTSRB datasets using 2D CNNs, and a public third party Trojaned model for vision tasks; ii) IMDB and consumer complaint datasets using both LSTM and 1D CNNs for text tasks; and speech command dataset using both 1D CNNs and 2D CNNs for audio tasks. Experimental results based on 28 tested Trojaned models demonstrate that STRIP-ViTA performs well across all nine architectures and five datasets. In general, STRIP-ViTA can effectively detect Trojan inputs with small false acceptance rate (FAR) with an acceptable preset false rejection rate (FRR). In particular, for vision tasks, we can always achieve a 0% FRR and FAR. By setting FRR to be 3%, average FAR of 1.1% and 3.55% are achieved for text and audio tasks, respectively. Moreover, we have evaluated and shown the effectiveness of STRIP-ViTA against a number of advanced backdoor attacks whilst other state-of-the-art methods lose effectiveness in front of one or all of these advanced backdoor attacks.

cs.CR↗

arXiv2019

Average-case Analysis of the Assignment Problem with Independent Preferences

The fundamental assignment problem is in search of welfare maximization mechanisms to allocate items to agents when the private preferences over indivisible items are provided by self-interested agents. The mainstream mechanism \textit{Random Priority} is asymptotically the best mechanism for this purpose, when comparing its welfare to the optimal social welfare using the canonical \textit{worst-case approximation ratio}. Despite its popularity, the efficiency loss indicated by the worst-case ratio does not have a constant bound. Recently, [Deng, Gao, Zhang 2017] show that when the agents' preferences are drawn from a uniform distribution, its \textit{average-case approximation ratio} is upper bounded by 3.718. They left it as an open question of whether a constant ratio holds for general scenarios. In this paper, we offer an affirmative answer to this question by showing that the ratio is bounded by $1/μ$ when the preference values are independent and identically distributed random variables, where $μ$ is the expectation of the value distribution. This upper bound also improves the upper bound of 3.718 in [Deng, Gao, Zhang 2017] for the Uniform distribution. Moreover, under mild conditions, the ratio has a \textit{constant} bound for any independent random values. En route to these results, we develop powerful tools to show the insights that in most instances the efficiency loss is small.

cs.GT↗

arXiv2019

Building Secure SRAM PUF Key Generators on Resource Constrained Devices

A securely maintained key is the premise upon which data stored and transmitted by ubiquitously deployed resource limited devices, such as those in the Internet of Things (IoT), are protected. However, many of these devices lack a secure non-volatile memory (NVM) for storing keys because of cost constraints. Silicon physical unclonable functions (PUFs) offering unique device specific secrets to electronic commodities are a low-cost alternative to secure NVM. As a physical hardware security primitive, reliability of a PUF is affected by thermal noise and changes in environmental conditions; consequently, PUF responses cannot be directly employed as cryptographic keys. A fuzzy extractor can turn noisy PUF responses into usable cryptographic keys. However, a fuzzy extractor is not immediately mountable on (highly) resource constrained devices due to its implementation overhead. We present a methodology for constructing a lightweight and secure PUF key generator for resource limited devices. In particular, we focus on PUFs constructed from pervasively embedded SRAM in modern microcontroller units and use a batteryless computational radio frequency identification (CRFID) device as a representative resource constrained IoT device in a case study.

cs.CR↗

arXiv2019

Hash Functions and Benchmarks for Resource Constrained Passive Devices: A Preliminary Study

Recently, we have witnessed the emergence of intermittently powered computational devices, an early example is the Intel WISP (Wireless Identification and Sensing Platform). How we engineer basic security services to realize mutual authentication, confidentiality and preserve privacy of information collected, stored and transmitted by, and establish the veracity of measurements taken from, such devices remain an open challenge; especially for batteryless and intermittently powered devices. While the cryptographic community has significantly progressed lightweight (in terms of area overhead) security primitives for low cost and power efficient hardware implementations, lightweight software implementations of security primitives for resource constrained devices are less investigated. Especially, the problem of providing security for intermittently powered computational devices is unexplored. In this paper, we illustrate the unique challenges posed by an emerging class of intermittently powered and energy constrained computational IoT devices for engineering security solutions. We focus on the construction and evaluation of a basic hash primitive---both existing cryptographic hash functions and non-cryptographic hash functions built upon lightweight block ciphers. We provide software implementation benchmarks for eight primitives on a low power and resource limited computational device, and outline an execution model for these primitives under intermittent powering.

cs.CR↗

arXiv2018

Lightweight (Reverse) Fuzzy Extractor with Multiple Referenced PUF Responses

A Physical unclonable functions (PUF), alike a fingerprint, exploits manufacturing randomness to endow each physical item with a unique identifier. One primary PUF application is the secure derivation of volatile cryptographic keys using a fuzzy extractor comprising of two procedures: i) secure sketch; and ii) entropy extraction. Although the entropy extractor can be lightweight, the overhead of the secure sketch responsible correcting naturally noisy PUF responses is usually costly. We observe that, in general, response unreliability with respect to a enrolled reference measurement increases with increasing differences between the in-the-field PUF operating condition and the operating condition used in evaluating the enrolled reference response. For the first time, we exploit such an important but inadvertent observation. In contrast to the conventional single reference response enrollment, we propose enrolling multiple reference responses (MRR) subject to the same challenge but under multiple distinct operating conditions. The critical observation here is that one of the reference operating conditions is likely to be closer to the operating condition of the field deployed PUF, thus, resulting in minimizing the expected unreliability when compared to the single reference under the nominal condition. Overall, MRR greatly reduces the demand for the expected number of erroneous bits for correction and, subsequently, achieve a significant reduction in the error correction overhead. The significant implementation efficiency gains from the proposed MRR method is demonstrated from software implementations of fuzzy extractors on batteryless resource constraint computational radio frequency identification devices, where realistic PUF data is collected from the embedded intrinsic SRAM PUFs.

cs.CR↗

arXiv2017

Smoothed and Average-case Approximation Ratios of Mechanisms: Beyond the Worst-case Analysis

The approximation ratio has become one of the dominant measures in mechanism design problems. In light of analysis of algorithms, we define the \emph{smoothed approximation ratio} to compare the performance of the optimal mechanism and a truthful mechanism when the inputs are subject to random perturbations of the worst-case inputs, and define the \emph{average-case approximation ratio} to compare the performance of these two mechanisms when the inputs follow a distribution. For the one-sided matching problem, \citet{FFZ:14} show that, amongst all truthful mechanisms, \emph{random priority} achieves the tight approximation ratio bound of $Θ(\sqrt{n})$. We prove that, despite of this worst-case bound, random priority has a \emph{constant smoothed approximation ratio}. This is, to our limited knowledge, the first work that asymptotically differentiates the smoothed approximation ratio from the worst-case approximation ratio for mechanism design problems. For the average-case, we show that our approximation ratio can be improved to $1+e$. These results partially explain why random priority has been successfully used in practice, although in the worst case the optimal social welfare is $Θ(\sqrt{n})$ times of what random priority achieves. These results also pave the way for further studies of smoothed and average-case analysis for approximate mechanism design problems, beyond the worst-case analysis.

cs.GT↗

arXiv2017

Modeling Attack Resilient Reconfigurable Latent Obfuscation Technique for PUF based Lightweight Authentication

Physical unclonable functions (PUFs), as hardware security primitives, exploit manufacturing randomness to extract hardware instance-specific secrets. One of most popular structures is time-delay based Arbiter PUF attributing to large number of challenge response pairs (CRPs) yielded and its compact realization. However, modeling building attacks threaten most variants of APUFs that are usually employed for strong PUF-oriented application---lightweight authentication---without reliance on the securely stored digital secrets based standard cryptographic protocols. In this paper, we investigate a reconfigurable latent obfuscation technique endowed PUF construction, coined as OB-PUF, to maintain the security of elementary PUF CRPs enabled authentication where a CRP is never used more than once. The obfuscation---determined by said random patterns---conceals and distorts the relationship between challenge-response pairs capable of thwarting a model building adversary needing to know the exact relationship between challenges and responses. A bit further, the obfuscation is hidden and reconfigured on demand, in other words, the patterns are not only invisible but also act as one-time pads that are only employed once per authentication around and then discarded. As a consequence, the OB-PUF demonstrates significant resistance to the recent revealed powerful Evaluation Strategy (ES) based modeling attacks where the direct relationship between challenge and response is even not a must. The OB-PUF's uniqueness and reliability metrics are also systematically studied followed by formal authentication capability evaluations.

cs.CR↗

arXiv2017

Detecting Recycled Commodity SoCs: Exploiting Aging-Induced SRAM PUF Unreliability

A physical unclonable function (PUF), analogous to a human fingerprint, has gained an enormous amount of attention from both academia and industry. SRAM PUF is among one of the popular silicon PUF constructions that exploits random initial power-up states from SRAM cells to extract hardware intrinsic secrets for identification and key generation applications. The advantage of SRAM PUFs is that they are widely embedded into commodity devices, thus such a PUF is obtained without a custom design and virtually free of implementation costs. A phenomenon known as `aging' alters the consistent reproducibility---reliability---of responses that can be extracted from a readout of a set of SRAM PUF cells. Similar to how a PUF exploits undesirable manufacturing randomness for generating a hardware intrinsic fingerprint, SRAM PUF unreliability induced by aging can be exploited to detect recycled commodity devices requiring no additional cost to the device. In this context, the SRAM PUF itself acts as an aging sensor by exploiting responses sensitive to aging. We use SRAMs available in pervasively deployed commercial off-the-shelf micro-controllers for experimental validations, which complements recent work demonstrated in FPGA platforms, and we present a simplified detection methodology along experimental results. We show that less than 1,000 SRAM responses are adequate to guarantee that both false acceptance rate and false rejection rate are no more than 0.001.

cs.CR↗

arXiv2017

R$^3$PUF: A Highly Reliable Memristive Device based Reconfigurable PUF

We present a memristive device based R$ ^3 $PUF construction achieving highly desired PUF properties, which are not offered by most current PUF designs: (1) High reliability, almost 100\% that is crucial for PUF-based cryptographic key generations, significantly reducing, or even eliminating the expensive overhead of on-chip error correction logic and the associated helper on-chip data storage or off-chip storage and transfer. (2) Reconfigurability, while current PUF designs rarely exhibit such an attractive property. We validate our R$ ^3 $PUF via extensive Monte-Carlo simulations in Cadence based on parameters of real devices. The R$ ^3 $PUF is simple, cost-effective and easy to manage compared to other PUF constructions exhibiting high reliability or reconfigurability. None of previous PUF constructions is able to provide both desired high reliability and reconfigurability concurrently.

cs.ET↗

arXiv2017

Exploiting PUF Models for Error Free Response Generation

Physical unclonable functions (PUF) extract secrets from randomness inherent in manufacturing processes. PUFs are utilized for basic cryptographic tasks such as authentication and key generation, and more recently, to realize key exchange and bit commitment requiring a large number of error free responses from a strong PUF. We propose an approach to eliminate the need to implement expensive on-chip error correction logic implementation and the associated helper data storage to reconcile naturally noisy PUF responses. In particular, we exploit a statistical model of an Arbiter PUF (APUF) constructed under the nominal operating condition during the challenge response enrollment phase by a trusted party to judiciously select challenges that yield error-free responses even across a wide operating conditions, specifically, a $ \pm 20\% $ supply voltage variation and a $ 40^{\crc} $ temperature variation. We validate our approach using measurements from two APUF datasets. Experimental results indicate that large number of error-free responses can be generated on demand under worst-case when PUF response error rate is up to 16.68\%.

cs.CR↗

arXiv2017

PUF-FSM: A Controlled Strong PUF

This paper presents the PUF finite state machine (PUF-FSM) that is served as a practical {\it controlled} strong PUF. Previous controlled PUF designs have the difficulties of stabilizing the noisy PUF responses where the error correction logic is required. In addition, the computed helper data to assist error correcting, however, leaks information, which poses the controlled PUF under the threatens of fault attacks or reliability-based attacks. The PUF-FSM eschews the error correction logic and the computation, storage and loading of the helper data on-chip by only employing error-free responses judiciously determined on demand in the absence of an Arbiter PUF with a large CRP space. In addition, the access to the PUF-FSM is controlled by the trusted entity. Control in means of i) restricting challenges presented to the PUF and ii) further preventing repeated response evaluations to gain unreliability side-channel information are foundations of defensing the most powerful modeling attacks. The PUF-FSM goes beyond authentications/identifications to such as key generations and advanced cryptographic applications built upon a shared key.

cs.CR↗