arXiv subjects

Ee-Chien Chang

Publications and source records attributed to Ee-Chien Chang.

At least 55 records · Page 3Linked to original sources

arXiv2023

Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation

Given a poorly documented neural network model, we take the perspective of a forensic investigator who wants to find out the model's data domain (e.g. whether on face images or traffic signs). Although existing methods such as membership inference and model inversion can be used to uncover some information about an unknown model, they still require knowledge of the data domain to start with. In this paper, we propose solving this problem by leveraging on comprehensive corpus such as ImageNet to select a meaningful distribution that is close to the original training distribution and leads to high performance in follow-up investigations. The corpus comprises two components, a large dataset of samples and meta information such as hierarchical structure and textual information on the samples. Our goal is to select a set of samples from the corpus for the given model. The core of our method is an objective function that considers two criteria on the selected samples: the model functional properties (derived from the dataset), and semantics (derived from the metadata). We also give an algorithm to efficiently search the large space of all possible subsets w.r.t. the objective function. Experimentation results show that the proposed method is effective. For example, cloning a given model (originally trained with CIFAR-10) by using Caltech 101 can achieve 45.5% accuracy. By using datasets selected by our method, the accuracy is improved to 72.0%.

cs.LG↗

arXiv2023

Projecting Non-Fungible Token (NFT) Collections: A Contextual Generative Approach

Non-fungible tokens (NFTs) are digital assets stored on a blockchain representing real-world objects such as art or collectibles. An NFT collection comprises numerous tokens; each token can be transacted multiple times. It is a multibillion-dollar market where the number of collections has more than doubled in 2022. In this paper, we want to obtain a generative model that, given the early transactions history (first quarter Q1) of a newly minted collection, generates subsequent transactions (quarters Q2, Q3, Q4), where the generative model is trained using the transaction history of a few mature collections. The goal is to use the generated transactions to project the potential market value of this newly minted collection over the next few quarters. A technical challenge exists in that different collections have diverse characteristics, and the generative model should generate based on the appropriate "contexts" of the collection. Our method takes a two-step approach. First, it employs unsupervised learning on the early transactions to extract characteristics (which we call contexts) of NFT collections. Next, it generates future transactions of each token based on these contexts and the early transactions, projecting the target collection's potential market value. Comprehensive experiments demonstrate our contextual generative approach's NFT projection capabilities.

q-fin.CP↗

arXiv2022

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

Deep neural networks are vulnerable to adversarial attacks. In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the particular model which the adversarial examples are generated from. Techniques derived would aid forensic investigation of attack incidents and serve as deterrence to potential attacks. We consider the buyers-seller setting where a machine learning model is to be distributed to various buyers and each buyer receives a slightly different copy with same functionality. A malicious buyer generates adversarial examples from a particular copy $\mathcal{M}_i$ and uses them to attack other copies. From these adversarial examples, the investigator wants to identify the source $\mathcal{M}_i$. To address this problem, we propose a two-stage separate-and-trace framework. The model separation stage generates multiple copies of a model for a same classification task. This process injects unique characteristics into each copy so that adversarial examples generated have distinct and traceable features. We give a parallel structure which embeds a ``tracer'' in each copy, and a noise-sensitive training loss to achieve this goal. The tracing stage takes in adversarial examples and a few candidate models, and identifies the likely source. Based on the unique features induced by the noise-sensitive loss function, we could effectively trace the potential adversarial copy by considering the output logits from each tracer. Empirical results show that it is possible to trace the origin of the adversarial example and the mechanism can be applied to a wide range of architectures and datasets.

cs.CR↗

arXiv2022

Purifier: Defending Data Inference Attacks via Transforming Confidence Scores

Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful information such as the membership, the reconstruction or the sensitive attributes of a data sample from the confidence scores predicted by the target classifier. In this paper, we propose a method, namely PURIFIER, to defend against membership inference attacks. It transforms the confidence score vectors predicted by the target classifier and makes purified confidence scores indistinguishable in individual shape, statistical distribution and prediction label between members and non-members. The experimental results show that PURIFIER helps defend membership inference attacks with high effectiveness and efficiency, outperforming previous defense methods, and also incurs negligible utility loss. Besides, our further experiments show that PURIFIER is also effective in defending adversarial model inversion attacks and attribute inference attacks. For example, the inversion error is raised about 4+ times on the Facescrub530 classifier, and the attribute inference accuracy drops significantly when PURIFIER is deployed in our experiment.

cs.LG↗

arXiv2022

Mixed Fault Tolerance Protocols with Trusted Execution Environment

Blockchain systems are designed, built and operated in the presence of failures. There are two dominant failure models, namely crash fault and Byzantine fault. Byzantine fault tolerance (BFT) protocols offer stronger security guarantees, and thus are widely used in blockchain systems. However, their security guarantees come at a dear cost to their performance and scalability. Several works have improved BFT protocols, and Trusted Execution Environment (TEE) has been shown to be an effective solution. However, existing such works typically assume that each participating node is equipped with TEE. For blockchain systems wherein participants typically have different hardware configurations, i.e., some nodes feature TEE while others do not, existing TEE-based BFT protocols are not applicable. This work studies the setting wherein not all participating nodes feature TEE, under which we propose a new fault model called mixed fault. We explore a new approach to designing efficient distributed fault-tolerant protocols under the mixed fault model. In general, mixed fault tolerance (MFT) protocols assume a network of $n$ nodes, among which up to $f = \frac{n-2}{3}$ can be subject to mixed faults. We identify two key principles for designing efficient MFT protocols, namely, (i) prioritizing non-equivocating nodes in leading the protocol, and (ii) advocating the use of public-key cryptographic primitives that allow authenticated messages to be aggregated. We showcase these design principles by prescribing an MFT protocol, namely MRaft. We implemented a prototype of MRaft using Intel SGX, integrated it into the CCF blockchain framework, conducted experiments, and showed that MFT protocols can obtain the same security guarantees as their BFT counterparts while still providing better performance (both transaction throughput and latency) and scalability.

cs.DC↗

arXiv2022

De-END: Decoder-driven Watermarking Network

With recent advances in machine learning, researchers are now able to solve traditional problems with new solutions. In the area of digital watermarking, deep-learning-based watermarking technique is being extensively studied. Most existing approaches adopt a similar encoder-driven scheme which we name END (Encoder-NoiseLayer-Decoder) architecture. In this paper, we revamp the architecture and creatively design a decoder-driven watermarking network dubbed De-END which greatly outperforms the existing END-based methods. The motivation for designing De-END originated from the potential drawback we discovered in END architecture: The encoder may embed redundant features that are not necessary for decoding, limiting the performance of the whole network. We conducted a detailed analysis and found that such limitations are caused by unsatisfactory coupling between the encoder and decoder in END. De-END addresses such drawbacks by adopting a Decoder-Encoder-Noiselayer-Decoder architecture. In De-END, the host image is firstly processed by the decoder to generate a latent feature map instead of being directly fed into the encoder. This latent feature map is concatenated to the original watermark message and then processed by the encoder. This change in design is crucial as it makes the feature of encoder and decoder directly shared thus the encoder and decoder are better coupled. We conducted extensive experiments and the results show that this framework outperforms the existing state-of-the-art (SOTA) END-based deep learning watermarking both in visual quality and robustness. On the premise of the same decoder structure, the visual quality (measured by PSNR) of De-END improves by 1.6dB (45.16dB to 46.84dB), and extraction accuracy after JPEG compression (QF=50) distortion outperforms more than 4% (94.9% to 99.1%).

cs.MM↗

arXiv2022

Scalable Private Decision Tree Evaluation with Sublinear Communication

Private decision tree evaluation (PDTE) allows a decision tree holder to run a secure protocol with a feature provider. By running the protocol, the feature provider will learn a classification result. Nothing more is revealed to either party. In most existing PDTE protocols, the required communication grows exponentially with the tree's depth $d$, which is highly inefficient for large trees. This shortcoming motivated us to design a sublinear PDTE protocol with $O(d)$ communication complexity. The core of our construction is a shared oblivious selection (SOS) functionality, allowing two parties to perform a secret-shared oblivious read operation from an array. We provide two SOS protocols, both of which achieve sublinear communication and propose optimizations to further improve their efficiency. Our sublinear PDTE protocol is based on the proposed SOS functionality and we prove its security under a semi-honest adversary. We compare our protocol with the state-of-the-art, in terms of communication and computation, under various network settings. The performance evaluation shows that our protocol is practical and more scalable over large trees than existing solutions.

cs.CR↗

arXiv2022

Poisoning Online Learning Filters: DDoS Attacks and Countermeasures

The recent advancements in machine learning have led to a wave of interest in adopting online learning-based approaches for long-standing attack mitigation issues. In particular, DDoS attacks remain a significant threat to network service availability even after more than two decades. These attacks have been well studied under the assumption that malicious traffic originates from a single attack profile. Based on this premise, malicious traffic characteristics are assumed to be considerably different from legitimate traffic. Consequently, online filtering methods are designed to learn network traffic distributions adaptively and rank requests according to their attack likelihood. During an attack, requests rated as malicious are precipitously dropped by the filters. In this paper, we conduct the first systematic study on the effects of data poisoning attacks on online DDoS filtering; introduce one such attack method, and propose practical protective countermeasures for these attacks. We investigate an adverse scenario where the attacker is "crafty", switching profiles during attacks and generating erratic attack traffic that is ever-shifting. This elusive attacker generates malicious requests by manipulating and shifting traffic distribution to poison the training data and corrupt the filters. To this end, we present a generative model MimicShift, capable of controlling traffic generation while retaining the originating traffic's intrinsic properties. Comprehensive experiments show that online learning filters are highly susceptible to poisoning attacks, sometimes performing much worse than a random filtering strategy in this attack scenario. At the same time, our proposed protective countermeasure diminishes the attack impact.

cs.CR↗

arXiv2021

SHADOWCAST: Controllable Graph Generation

We introduce the controllable graph generation problem, formulated as controlling graph attributes during the generative process to produce desired graphs with understandable structures. Using a transparent and straightforward Markov model to guide this generative process, practitioners can shape and understand the generated graphs. We propose ${\rm S{\small HADOW}C{\small AST}}$, a generative model capable of controlling graph generation while retaining the original graph's intrinsic properties. The proposed model is based on a conditional generative adversarial network. Given an observed graph and some user-specified Markov model parameters, ${\rm S{\small HADOW}C{\small AST}}$ controls the conditions to generate desired graphs. Comprehensive experiments on three real-world network datasets demonstrate our model's competitive performance in the graph generation task. Furthermore, we show its effective controllability by directing ${\rm S{\small HADOW}C{\small AST}}$ to generate hypothetical scenarios with different graph structures.

cs.LG↗

arXiv2021

Confusing and Detecting ML Adversarial Attacks with Injected Attractors

Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly. To confuse and detect such attacks, we take the proactive approach that modifies those functions with the goal of misleading the attacks to some local minimals, or to some designated regions that can be easily picked up by an analyzer. To achieve this goal, we propose adding a large number of artifacts, which we called $attractors$, onto the otherwise smooth function. An attractor is a point in the input space, where samples in its neighborhood have gradient pointing toward it. We observe that decoders of watermarking schemes exhibit properties of attractors and give a generic method that injects attractors from a watermark decoder into the victim model ${\mathcal M}$. This principled approach allows us to leverage on known watermarking schemes for scalability and robustness and provides explainability of the outcomes. Experimental studies show that our method has competitive performance. For instance, for un-targeted attacks on CIFAR-10 dataset, we can reduce the overall attack success rate of DeepFool to 1.9%, whereas known defense LID, FS and MagNet can reduce the rate to 90.8%, 98.5% and 78.5% respectively.

cs.CR↗

arXiv2020

Filtering DDoS Attacks from Unlabeled Network Traffic Data Using Online Deep Learning

DDoS attacks are simple, effective, and still pose a significant threat even after more than two decades. Given the recent success in machine learning, it is interesting to investigate how we can leverage deep learning to filter out application layer attack requests. There are challenges in adopting deep learning solutions due to the ever-changing profiles, the lack of labeled data, and constraints in the online setting. Offline unsupervised learning methods can sidestep these hurdles by learning an anomaly detector $N$ from the normal-day traffic ${\mathcal N}$. However, anomaly detection does not exploit information acquired during attacks, and their performance typically is not satisfactory. In this paper, we propose two frameworks that utilize both the historic ${\mathcal N}$ and the mixture ${\mathcal M}$ traffic obtained during attacks, consisting of unlabeled requests. We also introduce a machine learning optimization problem that aims to sift out the attacks using ${\mathcal N}$ and ${\mathcal M}$. First, our proposed approach, inspired by statistical methods, extends an unsupervised anomaly detector $N$ to solve the problem using estimated conditional probability distributions. We adopt transfer learning to apply $N$ on ${\mathcal N}$ and ${\mathcal M}$ separately and efficiently, combining the results to obtain an online learner. Second, we formulate a specific loss function more suited for deep learning and use iterative training to solve it in the online setting. On publicly available datasets, our online learners achieve a $99.3\%$ improvement on false-positive rates compared to the baseline detection methods. In the offline setting, our approaches are competitive with classifiers trained on labeled data.

cs.CR↗

arXiv2020

Defending Model Inversion and Membership Inference Attacks via Prediction Purification

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence scores predicted by the target classifier. In this paper, we propose a unified approach, namely purification framework, to defend data inference attacks. It purifies the confidence score vectors predicted by the target classifier by reducing their dispersion. The purifier can be further specialized in defending a particular attack via adversarial learning. We evaluate our approach on benchmark datasets and classifiers. We show that when the purifier is dedicated to one attack, it naturally defends the other one, which empirically demonstrates the connection between the two attacks. The purifier can effectively defend both attacks. For example, it can reduce the membership inference accuracy by up to 15% and increase the model inversion error by a factor of up to 4. Besides, it incurs less than 0.4% classification accuracy drop and less than 5.5% distortion to the confidence scores.

cs.CR↗

arXiv2020

Benefits and Pitfalls of Using Capture the Flag Games in University Courses

The concept of Capture the Flag (CTF) games for practicing cybersecurity skills is widespread in informal educational settings and leisure-time competitions. However, it is not much used in university courses. This paper summarizes our experience from using jeopardy CTF games as homework assignments in an introductory undergraduate course. Our analysis of data describing students' in-game actions and course performance revealed four aspects that should be addressed in the design of CTF tasks: scoring, scaffolding, plagiarism, and learning analytics capabilities of the used CTF platform. The paper addresses these aspects by sharing our recommendations. We believe that these recommendations are useful for cybersecurity instructors who consider using CTF games for assessment in university courses and developers of CTF game frameworks.

cs.CR↗

arXiv2020

Enhancing Transformation-based Defenses using a Distribution Classifier

Adversarial attacks on convolutional neural networks (CNN) have gained significant attention and there have been active research efforts on defense mechanisms. Stochastic input transformation methods have been proposed, where the idea is to recover the image from adversarial attack by random transformation, and to take the majority vote as consensus among the random samples. However, the transformation improves the accuracy on adversarial images at the expense of the accuracy on clean images. While it is intuitive that the accuracy on clean images would deteriorate, the exact mechanism in which how this occurs is unclear. In this paper, we study the distribution of softmax induced by stochastic transformations. We observe that with random transformations on the clean images, although the mass of the softmax distribution could shift to the wrong class, the resulting distribution of softmax could be used to correct the prediction. Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images. With these observations, we propose a method to improve existing transformation-based defenses. We train a separate lightweight distribution classifier to recognize distinct features in the distributions of softmax outputs of transformed images. Our empirical studies show that our distribution classifier, by training on distributions obtained from clean images only, outperforms majority voting for both clean and adversarial images. Our method is generic and can be integrated with existing transformation-based defenses.

cs.LG↗

arXiv2019

Self-Expiring Data Capsule using Trusted Execution Environment

Data privacy is unarguably of extreme importance. Nonetheless, there exist various daunting challenges to safe-guarding data privacy. These challenges stem from the fact that data owners have little control over their data once it has transgressed their local storage and been managed by third parties whose trustworthiness is questionable at times. Our work seeks to enhance data privacy by constructing a self-expiring data capsule. Sensitive data is encapsulated into a capsule which is associated with an access policy an expiring condition. The former indicates eligibility of functions that can access the data, and the latter dictates when the data should become inaccessible to anyone, including the previously eligible functions. Access to the data capsule, as well as its dismantling once the expiring condition is met, are governed by a committee of independent and mutually distrusting nodes. The pivotal contribution of our work is an integration of hardware primitive, state machine replication and threshold secret sharing in the design of the self-expiring data encapsulation framework. We implement the proposed framework in a system called TEEKAP. Our empirical experiments conducted on a realistic deployment setting with the access control committee spanning across four geographical regions reveal that TEEKAP can process access requests at scale with sub-second latency.

cs.CR↗

arXiv2019

Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking

The rise of machine learning as a service and model sharing platforms has raised the need of traitor-tracing the models and proof of authorship. Watermarking technique is the main component of existing methods for protecting copyright of models. In this paper, we show that distillation, a widely used transformation technique, is a quite effective attack to remove watermark embedded by existing algorithms. The fragility is due to the fact that distillation does not retain the watermark embedded in the model that is redundant and independent to the main learning task. We design ingrain in response to the destructive distillation. It regularizes a neural network with an ingrainer model, which contains the watermark, and forces the model to also represent the knowledge of the ingrainer. Our extensive evaluations show that ingrain is more robust to distillation attack and its robustness against other widely used transformation techniques is comparable to existing methods.

cs.CR↗

arXiv2019

Autonomous Membership Service for Enclave Applications

Trusted Execution Environment, or enclave, promises to protect data confidentiality and execution integrity of an outsourced computation on an untrusted host. Extending the protection to distributed applications that run on physically separated hosts, however, remains non-trivial. For instance, the current enclave provisioning model hinders elasticity of cloud applications. Furthermore, it remains unclear how an enclave process could verify if there exists another concurrently running enclave process instantiated using the same codebase, or count a number of such processes. In this paper, we seek an autonomous membership service for enclave applications. The application owner only needs to partake in instantiating the very first process of the application, whereas all subsequent process commission and decommission will be administered by existing and active processes of that very application. To achieve both safety and liveness, our protocol design admits unjust excommunication of a non-faulty process from the membership group. We implement the proposed membership service in a system called AMES. Our experimental study shows that AMES incurs an overhead of 5% - 16% compared to vanilla enclave execution.

cs.DC↗

arXiv2019

Towards Scaling Blockchain Systems via Sharding

Existing blockchain systems scale poorly because of their distributed consensus protocols. Current attempts at improving blockchain scalability are limited to cryptocurrency. Scaling blockchain systems under general workloads (i.e., non-cryptocurrency applications) remains an open question. In this work, we take a principled approach to apply sharding, which is a well-studied and proven technique to scale out databases, to blockchain systems in order to improve their transaction throughput at scale. This is challenging, however, due to the fundamental difference in failure models between databases and blockchain. To achieve our goal, we first enhance the performance of Byzantine consensus protocols, by doing so we improve individual shards' throughput. Next, we design an efficient shard formation protocol that leverages a trusted random beacon to securely assign nodes into shards. We rely on trusted hardware, namely Intel SGX, to achieve high performance for both consensus and shard formation protocol. Third, we design a general distributed transaction protocol that ensures safety and liveness even when transaction coordinators are malicious. Finally, we conduct an extensive evaluation of our design both on a local cluster and on Google Cloud Platform. The results show that our consensus and shard formation protocols outperform state-of-the-art solutions at scale. More importantly, our sharded blockchain reaches a high throughput that can handle Visa-level workloads, and is the largest ever reported in a realistic environment.

cs.DC↗