arXiv subjects

Tianwei Zhang

Publications and source records attributed to Tianwei Zhang.

At least 235 records · Page 13Linked to original sources

arXiv2023

A Benchmark of Long-tailed Instance Segmentation with Noisy Labels

In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reasons making this case realistic. First, datasets collected from real world usually obey a long-tailed distribution. Second, for instance segmentation datasets, as there are many instances in one image and some of them are tiny, it is easier to introduce noise into the annotations. Specifically, we propose a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation. Furthermore, we evaluate previous proposed instance segmentation algorithms on this dataset. The results indicate that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance, and inspire us to explore more effective approaches to address this practical challenge. The code and dataset are available in https://github.com/GuanlinLee/Noisy-LVIS.

cs.CV↗

arXiv2023

Multi-target Backdoor Attacks for Code Pre-trained Models

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting the scope of attacks. Moreover, the majority of attacks for pre-trained models are designed for understanding tasks. In this paper, we propose task-agnostic backdoor attacks for code pre-trained models. Our backdoored model is pre-trained with two learning strategies (i.e., Poisoned Seq2Seq learning and token representation learning) to support the multi-target attack of downstream code understanding and generation tasks. During the deployment phase, the implanted backdoors in the victim models can be activated by the designed triggers to achieve the targeted attack. We evaluate our approach on two code understanding tasks and three code generation tasks over seven datasets. Extensive experiments demonstrate that our approach can effectively and stealthily attack code-related downstream tasks.

cs.CR↗

arXiv2023

Extracting Cloud-based Model with Prior Knowledge

Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicious customers to conduct model extraction attacks, i.e., attackers can replicate a cloud-based black-box model merely via querying malicious examples. Existing model extraction attacks mainly depend on the posterior knowledge (i.e., predictions of query samples) from Oracle. Thus, they either require high query overhead to simulate the decision boundary, or suffer from generalization errors and overfitting problems due to query budget limitations. To mitigate it, this work proposes an efficient model extraction attack based on prior knowledge for the first time. The insight is that prior knowledge of unlabeled proxy datasets is conducive to the search for the decision boundary (e.g., informative samples). Specifically, we leverage self-supervised learning including autoencoder and contrastive learning to pre-compile the prior knowledge of the proxy dataset into the feature extractor of the substitute model. Then we adopt entropy to measure and sample the most informative examples to query the target model. Our design leverages both prior and posterior knowledge to extract the model and thus eliminates generalizability errors and overfitting problems. We conduct extensive experiments on open APIs like Traffic Recognition, Flower Recognition, Moderation Recognition, and NSFW Recognition from real-world platforms, Azure and Clarifai. The experimental results demonstrate the effectiveness and efficiency of our attack. For example, our attack achieves 95.1% fidelity with merely 1.8K queries (cost 2.16$) on the NSFW Recognition API. Also, the adversarial examples generated with our substitute model have better transferability than others, which reveals that our scheme is more conducive to downstream attacks.

cs.CR↗

arXiv2023

Backdoor Attacks with Input-unique Triggers in NLP

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems. Existing backdoor attacking systems face two severe issues:firstly, most backdoor triggers follow a uniform and usually input-independent pattern, e.g., insertion of specific trigger words, synonym replacement. This significantly hinders the stealthiness of the attacking model, leading the trained backdoor model being easily identified as malicious by model probes. Secondly, trigger-inserted poisoned sentences are usually disfluent, ungrammatical, or even change the semantic meaning from the original sentence, making them being easily filtered in the pre-processing stage. To resolve these two issues, in this paper, we propose an input-unique backdoor attack(NURA), where we generate backdoor triggers unique to inputs. IDBA generates context-related triggers by continuing writing the input with a language model like GPT2. The generated sentence is used as the backdoor trigger. This strategy not only creates input-unique backdoor triggers, but also preserves the semantics of the original input, simultaneously resolving the two issues above. Experimental results show that the IDBA attack is effective for attack and difficult to defend: it achieves high attack success rate across all the widely applied benchmarks, while is immune to existing defending methods. In addition, it is able to generate fluent, grammatical, and diverse backdoor inputs, which can hardly be recognized through human inspection.

cs.CL↗

arXiv2023

SoK: Rethinking Sensor Spoofing Attacks against Robotic Vehicles from a Systematic View

Robotic Vehicles (RVs) have gained great popularity over the past few years. Meanwhile, they are also demonstrated to be vulnerable to sensor spoofing attacks. Although a wealth of research works have presented various attacks, some key questions remain unanswered: are these existing works complete enough to cover all the sensor spoofing threats? If not, how many attacks are not explored, and how difficult is it to realize them? This paper answers the above questions by comprehensively systematizing the knowledge of sensor spoofing attacks against RVs. Our contributions are threefold. (1) We identify seven common attack paths in an RV system pipeline. We categorize and assess existing spoofing attacks from the perspectives of spoofer property, operation, victim characteristic and attack goal. Based on this systematization, we identify 4 interesting insights about spoofing attack designs. (2) We propose a novel action flow model to systematically describe robotic function executions and unexplored sensor spoofing threats. With this model, we successfully discover 103 spoofing attack vectors, 26 of which have been verified by prior works, while 77 attacks are never considered. (3) We design two novel attack methodologies to verify the feasibility of newly discovered spoofing attack vectors.

cs.CR↗

arXiv2023

Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication

Training Graph Neural Networks (GNNs) on large graphs is challenging due to the conflict between the high memory demand and limited GPU memory. Recently, distributed full-graph GNN training has been widely adopted to tackle this problem. However, the substantial inter-GPU communication overhead can cause severe throughput degradation. Existing communication compression techniques mainly focus on traditional DNN training, whose bottleneck lies in synchronizing gradients and parameters. We find they do not work well in distributed GNN training as the barrier is the layer-wise communication of features during the forward pass & feature gradients during the backward pass. To this end, we propose an efficient distributed GNN training framework Sylvie, which employs one-bit quantization technique in GNNs and further pipelines the curtailed communication with computation to enormously shrink the overhead while maintaining the model quality. In detail, Sylvie provides a lightweight Low-bit Module to quantize the sent data and dequantize the received data back to full precision values in each layer. Additionally, we propose a Bounded Staleness Adaptor to control the introduced staleness to achieve further performance enhancement. We conduct theoretical convergence analysis and extensive experiments on various models & datasets to demonstrate Sylvie can considerably boost the training throughput by up to 28.1x.

cs.DC↗

arXiv2023

Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks

Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary could tamper with a small number of model parameter bits to break the integrity of DNNs. To mitigate such threats, a batch of defense methods are proposed, focusing on the untargeted scenarios. Unfortunately, they either require extra trustworthy applications or make models more vulnerable to targeted BFAs. Countermeasures against targeted BFAs, stealthier and more purposeful by nature, are far from well established. In this work, we propose Aegis, a novel defense method to mitigate targeted BFAs. The core observation is that existing targeted attacks focus on flipping critical bits in certain important layers. Thus, we design a dynamic-exit mechanism to attach extra internal classifiers (ICs) to hidden layers. This mechanism enables input samples to early-exit from different layers, which effectively upsets the adversary's attack plans. Moreover, the dynamic-exit mechanism randomly selects ICs for predictions during each inference to significantly increase the attack cost for the adaptive attacks where all defense mechanisms are transparent to the adversary. We further propose a robustness training strategy to adapt ICs to the attack scenarios by simulating BFAs during the IC training phase, to increase model robustness. Extensive evaluations over four well-known datasets and two popular DNN structures reveal that Aegis could effectively mitigate different state-of-the-art targeted attacks, reducing attack success rate by 5-10$\times$, significantly outperforming existing defense methods.

cs.CR↗

arXiv2023

Smaller Is Bigger: Rethinking the Embedding Rate of Deep Hiding

Deep hiding, concealing secret information using Deep Neural Networks (DNNs), can significantly increase the embedding rate and improve the efficiency of secret sharing. Existing works mainly force on designing DNNs with higher embedding rates or fancy functionalities. In this paper, we want to answer some fundamental questions: how to increase and what determines the embedding rate of deep hiding. To this end, we first propose a novel Local Deep Hiding (LDH) scheme that significantly increases the embedding rate by hiding large secret images into small local regions of cover images. Our scheme consists of three DNNs: hiding, locating, and revealing. We use the hiding network to convert a secret image in a small imperceptible compact secret code that is embedded into a random local region of a cover image. The locating network assists the revealing process by identifying the position of secret codes in the stego image, while the revealing network recovers all full-size secret images from these identified local regions. Our LDH achieves an extremely high embedding rate, i.e., $16\times24$ bpp and exhibits superior robustness to common image distortions. We also conduct comprehensive experiments to evaluate our scheme under various system settings. We further quantitatively analyze the trade-off between the embedding rate and image quality with different image restoration algorithms.

cs.MM↗

arXiv2022

Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge devices and cloud servers). In this paper, we propose a novel backdoor attack specifically on the dynamic multi-exit DNN models. Particularly, we inject a backdoor by poisoning one DNN model's shallow hidden layers targeting not this vanilla DNN model but only its dynamically deployed multi-exit architectures. Our backdoored vanilla model behaves normally on performance and cannot be activated even with the correct trigger. However, the backdoor will be activated when the victims acquire this model and transform it into a dynamic multi-exit architecture at their deployment. We conduct extensive experiments to prove the effectiveness of our attack on three structures (ResNet-56, VGG-16, and MobileNet) with four datasets (CIFAR-10, SVHN, GTSRB, and Tiny-ImageNet) and our backdoor is stealthy to evade multiple state-of-the-art backdoor detection or removal methods.

cs.CR↗

arXiv2022

GNN-SL: Sequence Labeling Based on Nearest Examples via GNN

To better handle long-tail cases in the sequence labeling (SL) task, in this work, we introduce graph neural networks sequence labeling (GNN-SL), which augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. Since not all the retrieved tagging examples benefit the model prediction, we construct a heterogeneous graph, and leverage graph neural networks (GNNs) to transfer information between the retrieved tagging examples and the input word sequence. The augmented node which aggregates information from neighbors is used to do prediction. This strategy enables the model to directly acquire similar tagging examples and improves the general quality of predictions. We conduct a variety of experiments on three typical sequence labeling tasks: Named Entity Recognition (NER), Part of Speech Tagging (POS), and Chinese Word Segmentation (CWS) to show the significant performance of our GNN-SL. Notably, GNN-SL achieves SOTA results of 96.9 (+0.2) on PKU, 98.3 (+0.4) on CITYU, 98.5 (+0.2) on MSR, and 96.9 (+0.2) on AS for the CWS task, and results comparable to SOTA performances on NER datasets, and POS datasets.

cs.CL↗

arXiv2022

Efficiency Boosting of Secure Cross-platform Recommender Systems over Sparse Data

Fueled by its successful commercialization, the recommender system (RS) has gained widespread attention. However, as the training data fed into the RS models are often highly sensitive, it ultimately leads to severe privacy concerns, especially when data are shared among different platforms. In this paper, we follow the tune of existing works to investigate the problem of secure sparse matrix multiplication for cross-platform RSs. Two fundamental while critical issues are addressed: preserving the training data privacy and breaking the data silo problem. Specifically, we propose two concrete constructions with significantly boosted efficiency. They are designed for the sparse location insensitive case and location sensitive case, respectively. State-of-the-art cryptography building blocks including homomorphic encryption (HE) and private information retrieval (PIR) are fused into our protocols with non-trivial optimizations. As a result, our schemes can enjoy the HE acceleration technique without privacy trade-offs. We give formal security proofs for the proposed schemes and conduct extensive experiments on both real and large-scale simulated datasets. Compared with state-of-the-art works, our two schemes compress the running time roughly by 10* and 2.8*. They also attain up to 15* and 2.3* communication reduction without accuracy loss.

cs.CR↗

arXiv2022

Fast Nearest Neighbor Machine Translation

Though nearest neighbor Machine Translation ($k$NN-MT) \citep{khandelwal2020nearest} has proved to introduce significant performance boosts over standard neural MT systems, it is prohibitively slow since it uses the entire reference corpus as the datastore for the nearest neighbor search. This means each step for each beam in the beam search has to search over the entire reference corpus. $k$NN-MT is thus two-orders slower than vanilla MT models, making it hard to be applied to real-world applications, especially online services. In this work, we propose Fast $k$NN-MT to address this issue. Fast $k$NN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast $k$NN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token. Then at each decoding step, in contrast to using the entire corpus as the datastore, the search space is limited to target tokens corresponding to the previously selected reference source tokens. This strategy avoids search through the whole datastore for nearest neighbors and drastically improves decoding efficiency. Without loss of performance, Fast $k$NN-MT is two-orders faster than $k$NN-MT, and is only two times slower than the standard NMT model. Fast $k$NN-MT enables the practical use of $k$NN-MT systems in real-world MT applications. The code is available at \url{https://github.com/ShannonAI/fast-knn-nmt}

cs.CL↗

arXiv2022

Whole-Body Control for Velocity-Controlled Mobile Collaborative Robots Using Coupling Dynamic Movement Primitives

In this paper, we propose a unified whole-body control framework for velocity-controlled mobile collaborative robots which can distribute task motion into the arm and mobile base according to specific task requirements by adjusting weighting factors. Our framework focuses on addressing two challenging issues in whole-body coordination: 1) different dynamic characteristics of the mobile base and the arm; 2) avoidance of violating both safety and configuration constraints. In addition, our controller involves Coupling Dynamic Movement Primitives to enable the essential capabilities for collaboration and interaction applications, such as obstacle avoidance, human teaching, and compliance control. Based on these, we design an adaptive motion mode for intuitive physical human-robot interaction through adjusting the weighting factors. The proposed controller is in closed-form and thus quite computationally efficient. Several typical experiments carried out on a real mobile collaborative robot validate the effectiveness of the proposed controller.

cs.RO↗

arXiv2022

SIMC 2.0: Improved Secure ML Inference Against Malicious Clients

In this paper, we study the problem of secure ML inference against a malicious client and a semi-trusted server such that the client only learns the inference output while the server learns nothing. This problem is first formulated by Lehmkuhl \textit{et al.} with a solution (MUSE, Usenix Security'21), whose performance is then substantially improved by Chandran et al.'s work (SIMC, USENIX Security'22). However, there still exists a nontrivial gap in these efforts towards practicality, giving the challenges of overhead reduction and secure inference acceleration in an all-round way. We propose SIMC 2.0, which complies with the underlying structure of SIMC, but significantly optimizes both the linear and non-linear layers of the model. Specifically, (1) we design a new coding method for homomorphic parallel computation between matrices and vectors. It is custom-built through the insight into the complementarity between cryptographic primitives in SIMC. As a result, it can minimize the number of rotation operations incurred in the calculation process, which is very computationally expensive compared to other homomorphic operations e.g., addition, multiplication). (2) We reduce the size of the garbled circuit (GC) (used to calculate nonlinear activation functions, e.g., ReLU) in SIMC by about two thirds. Then, we design an alternative lightweight protocol to perform tasks that are originally allocated to the expensive GCs. Compared with SIMC, our experiments show that SIMC 2.0 achieves a significant speedup by up to $17.4\times $ for linear layer computation, and at least $1.3\times$ reduction of both the computation and communication overheads in the implementation of non-linear layers under different data dimensions. Meanwhile, SIMC 2.0 demonstrates an encouraging runtime boost by $2.3\sim 4.3\times$ over SIMC on different state-of-the-art ML models.

cs.CR↗

arXiv2022

Cache Refinement Type for Side-Channel Detection of Cryptographic Software

Cache side-channel attacks exhibit severe threats to software security and privacy, especially for cryptosystems. In this paper, we propose CaType, a novel refinement type-based tool for detecting cache side channels in crypto software. Compared to previous works, CaType provides the following advantages: (1) For the first time CaType analyzes cache side channels using refinement type over x86 assembly code. It reveals several significant and effective enhancements with refined types, including bit-level granularity tracking, distinguishing different effects of variables, precise type inferences, and high scalability. (2) CaType is the first static analyzer for crypto libraries in consideration of blinding-based defenses. (3) From the perspective of implementation, CaType uses cache layouts of potential vulnerable control-flow branches rather than cache states to suppress false positives. We evaluate CaType in identifying side channel vulnerabilities in real-world crypto software, including RSA, ElGamal, and (EC)DSA from OpenSSL and Libgcrypt. CaType captures all known defects, detects previously-unknown vulnerabilities, and reveals several false positives of previous tools. In terms of performance, CaType is 16X faster than CacheD and 131X faster than CacheS when analyzing the same libraries. These evaluation results confirm the capability of CaType in identifying side channel defects with great precision, efficiency, and scalability.

cs.CR↗

arXiv2022

RGB-D SLAM in Indoor Planar Environments with Multiple Large Dynamic Objects

This work presents a novel dense RGB-D SLAM approach for dynamic planar environments that enables simultaneous multi-object tracking, camera localisation and background reconstruction. Previous dynamic SLAM methods either rely on semantic segmentation to directly detect dynamic objects; or assume that dynamic objects occupy a smaller proportion of the camera view than the static background and can, therefore, be removed as outliers. Our approach, however, enables dense SLAM when the camera view is largely occluded by multiple dynamic objects with the aid of camera motion prior. The dynamic planar objects are separated by their different rigid motions and tracked independently. The remaining dynamic non-planar areas are removed as outliers and not mapped into the background. The evaluation demonstrates that our approach outperforms the state-of-the-art methods in terms of localisation, mapping, dynamic segmentation and object tracking. We also demonstrate its robustness to large drift in the camera motion prior.

cs.RO↗

arXiv2022

VerifyML: Obliviously Checking Model Fairness Resilient to Malicious Model Holder

In this paper, we present VerifyML, the first secure inference framework to check the fairness degree of a given Machine learning (ML) model. VerifyML is generic and is immune to any obstruction by the malicious model holder during the verification process. We rely on secure two-party computation (2PC) technology to implement VerifyML, and carefully customize a series of optimization methods to boost its performance for both linear and nonlinear layer execution. Specifically, (1) VerifyML allows the vast majority of the overhead to be performed offline, thus meeting the low latency requirements for online inference. (2) To speed up offline preparation, we first design novel homomorphic parallel computing techniques to accelerate the authenticated Beaver's triple (including matrix-vector and convolution triples) generation procedure. It achieves up to $1.7\times$ computation speedup and gains at least $10.7\times$ less communication overhead compared to state-of-the-art work. (3) We also present a new cryptographic protocol to evaluate the activation functions of non-linear layers, which is $4\times$--$42\times$ faster and has $>48\times$ lesser communication than existing 2PC protocol against malicious parties. In fact, VerifyML even beats the state-of-the-art semi-honest ML secure inference system! We provide formal theoretical analysis for VerifyML security and demonstrate its performance superiority on mainstream ML models including ResNet-18 and LeNet.

cs.CR↗

arXiv2022

New Secure Sparse Inner Product with Applications to Machine Learning

Sparse inner product (SIP) has the attractive property of overhead being dominated by the intersection of inputs between parties, independent of the actual input size. It has intriguing prospects, especially for boosting machine learning on large-scale data, which is tangled with sparse data. In this paper, we investigate privacy-preserving SIP problems that have rarely been explored before. Specifically, we propose two concrete constructs, one requiring offline linear communication which can be amortized across queries, while the other has sublinear overhead but relies on the more computationally expensive tool. Our approach exploits state-of-the-art cryptography tools including garbled Bloom filters (GBF) and Private Information Retrieval (PIR) as the cornerstone, but carefully fuses them to obtain non-trivial overhead reductions. We provide formal security analysis of the proposed constructs and implement them into representative machine learning algorithms including k-nearest neighbors, naive Bayes classification and logistic regression. Compared to the existing efforts, our method achieves $2$-$50\times$ speedup in runtime and up to $10\times$ reduction in communication.

cs.CR↗