Searcharxiv⌕ Search

arXiv subjects

Jun Sun

Publications and source records attributed to Jun Sun.

At least 163 records · Page 9Linked to original sources
arXiv2023

RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates

Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest. In this paper, we investigate two challenging problems: 1) when modality missing exists in the training data, how to exploit the incomplete samples while guaranteeing that they are properly supervised? 2) when the missing rates of different modalities vary, causing or exacerbating the imbalance among modalities, how to address the imbalance and ensure all modalities are well-trained? To tackle these two challenges, we first introduce the variational information bottleneck (VIB) method for the cross-modal representation learning of missing modalities, which capitalizes on the available modalities and the labels as supervision. Then, accounting for the imbalanced missing rates, we define relative advantage to quantify the advantage of each modality over others. Accordingly, a bi-level optimization problem is formulated to adaptively regulate the supervision of all modalities during training. As a whole, the proposed approach features \textbf{Re}lative a\textbf{d}vantage aware \textbf{C}ross-m\textbf{o}dal \textbf{r}epresentation l\textbf{e}arning (abbreviated as \textbf{RedCore}) for missing modalities with imbalanced missing rates. Extensive empirical results demonstrate that RedCore outperforms competing models in that it exhibits superior robustness against either large or imbalanced missing rates.

cs.LG↗
arXiv2023

Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep learning models, where hidden backdoors are activated by triggers embedded by the attacker, thereby outputting malicious predictions that may not align with the intended output for a given input. In this work, we propose a novel black-box backdoor attack based on machine unlearning. The attacker first augments the training set with carefully designed samples, including poison and mitigation data, to train a `benign' model. Then, the attacker posts unlearning requests for the mitigation samples to remove the impact of relevant data on the model, gradually activating the hidden backdoor. Since backdoors are implanted during the iterative unlearning process, it significantly increases the computational overhead of existing defense methods for backdoor detection or mitigation. To address this new security threat, we proposes two methods for detecting or mitigating such malicious unlearning requests. We conduct the experiment in both exact unlearning and approximate unlearning (i.e., SISA) settings. Experimental results indicate that: 1) our attack approach can successfully implant backdoor into the model, and sharding increases the difficult of attack; 2) our detection algorithms are effective in identifying the mitigation samples, while sharding reduces the effectiveness of our detection algorithms.

cs.CR↗
arXiv2023

Causality Analysis for Evaluating the Security of Large Language Models

Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF), recent studies have shown that LLMs are still subject to attacks such as adversarial perturbation and Trojan attacks. Further research is thus needed to evaluate their security and/or understand the lack of it. In this work, we propose a framework for conducting light-weight causality-analysis of LLMs at the token, layer, and neuron level. We applied our framework to open-source LLMs such as Llama2 and Vicuna and had multiple interesting discoveries. Based on a layer-level causality analysis, we show that RLHF has the effect of overfitting a model to harmful prompts. It implies that such security can be easily overcome by `unusual' harmful prompts. As evidence, we propose an adversarial perturbation method that achieves 100\% attack success rate on the red-teaming tasks of the Trojan Detection Competition 2023. Furthermore, we show the existence of one mysterious neuron in both Llama2 and Vicuna that has an unreasonably high causal effect on the output. While we are uncertain on why such a neuron exists, we show that it is possible to conduct a ``Trojan'' attack targeting that particular neuron to completely cripple the LLM, i.e., we can generate transferable suffixes to prompts that frequently make the LLM produce meaningless responses.

cs.AI↗
arXiv2023

Prompting Frameworks for Large Language Models: A Survey

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where "prompt'' plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: 1) temporal lag of training data, and 2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power of LLMs for downstream tasks, but a lack of systematic literature and standardized terminology, partly due to the rapid evolution of this field. Therefore, in this work, we survey related prompting tools and promote the concept of the "Prompting Framework" (PF), i.e. the framework for managing, simplifying, and facilitating interaction with large language models. We define the lifecycle of the PF as a hierarchical structure, from bottom to top, namely: Data Level, Base Level, Execute Level, and Service Level. We also systematically depict the overall landscape of the emerging PF field and discuss potential future research and challenges. To continuously track the developments in this area, we maintain a repository at https://github.com/lxx0628/Prompting-Framework-Survey, which can be a useful resource sharing platform for both academic and industry in this field.

cs.SE↗
arXiv2023

Configuring Timing Parameters to Ensure Execution-Time Opacity in Timed Automata

Timing information leakage occurs whenever an attacker successfully deduces confidential internal information by observing some timed information such as events with timestamps. Timed automata are an extension of finite-state automata with a set of clocks evolving linearly and that can be tested or reset, making this formalism able to reason on systems involving concurrency and timing constraints. In this paper, we summarize a recent line of works using timed automata as the input formalism, in which we assume that the attacker has access (only) to the system execution time. First, we address the following execution-time opacity problem: given a timed system modeled by a timed automaton, given a secret location and a final location, synthesize the execution times from the initial location to the final location for which one cannot deduce whether the secret location was visited. This means that for any such execution time, the system is opaque: either the final location is not reachable, or it is reachable with that execution time for both a run visiting and a run not visiting the secret location. We also address the full execution-time opacity problem, asking whether the system is opaque for all execution times; we also study a weak counterpart. Second, we add timing parameters, which are a way to configure a system: we identify a subclass of parametric timed automata with some decidability results. In addition, we devise a semi-algorithm for synthesizing timing parameter valuations guaranteeing that the resulting system is opaque. Third, we report on problems when the secret has itself an expiration date, thus defining expiring execution-time opacity problems. We finally show that our method can also apply to program analysis with configurable internal timings.

cs.LO↗
arXiv2023

Unexpected Reversed Piezoelectric Response in Elemental Sb and Bi Monolayers

Sb and Bi monolayers, as single-elemental ferroelectric materials with similar atomic structure, hold intrinsic piezoelectricity theoretically, which makes them highly promising for applications in functional nano-devices such as sensors and actuators. Here, using first-principles calculations, we systematically explore the piezoelectric response of Sb and Bi monolayers. Our findings reveal that Sb exhibits a negative piezoelectric response, whereas Bi displays a positive one. This discrepancy is attributed to the dominant role of different atomic internal distortions (internal-strain terms) in response to applied strain. Further electron-density distribution analysis reveals that the atomic bonding in Sb tends to be covalent, while the atomic bonding in Bi leans more towards ionic. Compared to the Sb monolayer, the Bi monolayer is distinguished by its more pronounced lone-pair orbitals electrons and associated larger Born effective charges. The Coulomb repulsions between lone-pair orbitals electrons and the chemical bonds lead to the Bi monolayer possessing more prominent atomic folds and, consequently, more significant atomic distortion in the z-direction under strain. These differences result in a considerable difference in internal-strain terms, ultimately leading to the reversed piezoelectric response between Sb and Bi monolayers. The present work provides valuable insights into the piezoelectric mechanism of 2D ferroelectric materials and their potential applications in nano-electronic devices.

cond-mat.mtrl-sci↗
arXiv2023

K-ST: A Formal Executable Semantics of the Structured Text Language for PLCs

Programmable Logic Controllers (PLCs) are responsible for automating process control in many industrial systems (e.g. in manufacturing and public infrastructure), and thus it is critical to ensure that they operate correctly and safely. The majority of PLCs are programmed in languages such as Structured Text (ST). However, a lack of formal semantics makes it difficult to ascertain the correctness of their translators and compilers, which vary from vendor-to-vendor. In this work, we develop K-ST, a formal executable semantics for ST in the K framework. Defined with respect to the IEC 61131-3 standard and PLC vendor manuals, K-ST is a high-level reference semantics that can be used to evaluate the correctness and consistency of different ST implementations. We validate K-ST by executing 509 ST programs extracted from Github and comparing the results against existing commercial compilers (i.e., CODESYS, CX-Programmer, and GX Works2). We then apply K-ST to validate the implementation of the open source OpenPLC platform, comparing the executions of several test programs to uncover five bugs and nine functional defects in the compiler.

cs.PL↗
arXiv2023

Towards Certified Probabilistic Robustness with High Accuracy

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably robust yet accurate neural network models remains an open problem. For example, adversarial training improves empirical robustness, but they do not provide certification of the model's robustness. On the other hand, certified training provides certified robustness but at the cost of a significant accuracy drop. In this work, we propose a novel approach that aims to achieve both high accuracy and certified probabilistic robustness. Our method has two parts, i.e., a probabilistic robust training method with an additional goal of minimizing variance in terms of divergence and a runtime inference method for certified probabilistic robustness of the prediction. The latter enables efficient certification of the model's probabilistic robustness at runtime with statistical guarantees. This is supported by our training objective, which minimizes the variance of the model's predictions in a given vicinity, derived from a general definition of model robustness. Our approach works for a variety of perturbations and is reasonably efficient. Our experiments on multiple models trained on different datasets demonstrate that our approach significantly outperforms existing approaches in terms of both certification rate and accuracy.

cs.LG↗
arXiv2023

Analyzing and controlling diversity in quantum-behaved particle swarm optimization

This paper addresses the issues of controlling and analyzing the population diversity in quantum-behaved particle swarm optimization (QPSO), which is an optimization approach motivated by concepts in quantum mechanics and PSO. In order to gain an in-depth understanding of the role the diversity plays in the evolving process, we first define the genotype diversity by the distance to the average point of the particles' positions and the phenotype diversity by the fitness values for the QPSO. Then, the correlations between the two types of diversities and the search performance are tested and analyzed on several benchmark functions, and the distance-to-average-point diversity is showed to have stronger association with the search performance during the evolving processes. Finally, in the light of the performed diversity analyses, two strategies for controlling the distance-to-average-point diversities are proposed for the purpose of improving the search ability of the QPSO algorithm. Empirical studies on the QPSO with the introduced diversity control methods are performed on a set of benchmark functions from the CEC 2005 benchmark suite. The performance of the proposed methods are evaluated and compared with the original QPSO and other PSO variants.

cs.NE↗
arXiv2023

Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework

Machine learning is widely used to make decisions with societal impact such as bank loan approving, criminal sentencing, and resume filtering. How to ensure its fairness while maintaining utility is a challenging but crucial issue. Fairness is a complex and context-dependent concept with over 70 different measurement metrics. Since existing regulations are often vague in terms of which metric to use and different organizations may prefer different fairness metrics, it is important to have means of improving fairness comprehensively. Existing mitigation techniques often target at one specific fairness metric and have limitations in improving multiple notions of fairness simultaneously. In this work, we propose CFU (Comprehensive Fairness-Utility), a reinforcement learning-based framework, to efficiently improve the fairness-utility trade-off in machine learning classifiers. A comprehensive measurement that can simultaneously consider multiple fairness notions as well as utility is established, and new metrics are proposed based on an in-depth analysis of the relationship between different fairness metrics. The reward function of CFU is constructed with comprehensive measurement and new metrics. We conduct extensive experiments to evaluate CFU on 6 tasks, 3 machine learning models, and 15 fairness-utility measurements. The results demonstrate that CFU can improve the classifier on multiple fairness metrics without sacrificing its utility. It outperforms all state-of-the-art techniques and has witnessed a 37.5% improvement on average.

cs.LG↗
arXiv2023

Fuzzing with Quantitative and Adaptive Hot-Bytes Identification

Fuzzing has emerged as a powerful technique for finding security bugs in complicated real-world applications. American fuzzy lop (AFL), a leading fuzzing tool, has demonstrated its powerful bug finding ability through a vast number of reported CVEs. However, its random mutation strategy is unable to generate test inputs that satisfy complicated branching conditions (e.g., magic-byte comparisons, checksum tests, and nested if-statements), which are commonly used in image decoders/encoders, XML parsers, and checksum tools. Existing approaches (such as Steelix and Neuzz) on addressing this problem assume unrealistic assumptions such as we can satisfy the branch condition byte-to-byte or we can identify and focus on the important bytes in the input (called hot-bytes) once and for all. In this work, we propose an approach called \tool~which is designed based on the following principles. First, there is a complicated relation between inputs and branching conditions and thus we need not only an expressive model to capture such relationship but also an informative measure so that we can learn such relationship effectively. Second, different branching conditions demand different hot-bytes and we must adjust our fuzzing strategy adaptively depending on which branches are the current bottleneck. We implement our approach as an open source project and compare its efficiency with other state-of-the-art fuzzers. Our evaluation results on 10 real-world programs and LAVA-M dataset show that \tool~achieves sustained increases in branch coverage and discovers more bugs than other fuzzers.

cs.CR↗
arXiv2023

The role of high-order anharmonicity and off-diagonal terms in thermal conductivity: a case study of multi-phase CsPbBr3

We investigate the influence of three- and four-phonon scattering, perturbative anharmonic phonon renormalization, and off-diagonal terms of coherent phonons on the thermal conductivity of CsPbBr3 phase change perovskite, by using advanced implementations and first-principles simulations. Our study spans a wide temperature range covering the entire structural spectrum. Notably, we demonstrate that the interactions between acoustic and optical phonons result in contrasting trends of phonon frequency shifts for the high-lying optical phonons in orthorhombic and cubic CsPbBr3 as temperature varies. Our findings highlight the significance of wave-like tunneling of coherent phonons in ultralow and glass-like thermal conductivity in halide perovskites.

cond-mat.mtrl-sci↗
arXiv2023

Semantic-Based Neural Network Repair

Recently, neural networks have spread into numerous fields including many safety-critical systems. Neural networks are built (and trained) by programming in frameworks such as TensorFlow and PyTorch. Developers apply a rich set of pre-defined layers to manually program neural networks or to automatically generate them (e.g., through AutoML). Composing neural networks with different layers is error-prone due to the non-trivial constraints that must be satisfied in order to use those layers. In this work, we propose an approach to automatically repair erroneous neural networks. The challenge is in identifying a minimal modification to the network so that it becomes valid. Modifying a layer might have cascading effects on subsequent layers and thus our approach must search recursively to identify a "globally" minimal modification. Our approach is based on an executable semantics of deep learning layers and focuses on four kinds of errors which are common in practice. We evaluate our approach for two usage scenarios, i.e., repairing automatically generated neural networks and manually written ones suffering from common model bugs. The results show that we are able to repair 100% of a set of randomly generated neural networks (which are produced with an existing AI framework testing approach) effectively and efficiently (with an average repair time of 21.08s) and 93.75% of a collection of real neural network bugs (with an average time of 3min 40s).

cs.LG↗
arXiv2023

QEBVerif: Quantization Error Bound Verification of Neural Networks

To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge devices, quantization is widely regarded as one promising technique. It reduces the resource requirements for computational power and storage space by quantizing the weights and/or activation tensors of a DNN into lower bit-width fixed-point numbers, resulting in quantized neural networks (QNNs). While it has been empirically shown to introduce minor accuracy loss, critical verified properties of a DNN might become invalid once quantized. Existing verification methods focus on either individual neural networks (DNNs or QNNs) or quantization error bound for partial quantization. In this work, we propose a quantization error bound verification method, named QEBVerif, where both weights and activation tensors are quantized. QEBVerif consists of two parts, i.e., a differential reachability analysis (DRA) and a mixed-integer linear programming (MILP) based verification method. DRA performs difference analysis between the DNN and its quantized counterpart layer-by-layer to compute a tight quantization error interval efficiently. If DRA fails to prove the error bound, then we encode the verification problem into an equivalent MILP problem which can be solved by off-the-shelf solvers. Thus, QEBVerif is sound, complete, and reasonably efficient. We implement QEBVerif and conduct extensive experiments, showing its effectiveness and efficiency.

cs.LG↗
arXiv2023

Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection

Most anomaly detection (AD) models are learned using only normal samples in an unsupervised way, which may result in ambiguous decision boundary and insufficient discriminability. In fact, a few anomaly samples are often available in real-world applications, the valuable knowledge of known anomalies should also be effectively exploited. However, utilizing a few known anomalies during training may cause another issue that the model may be biased by those known anomalies and fail to generalize to unseen anomalies. In this paper, we tackle supervised anomaly detection, i.e., we learn AD models using a few available anomalies with the objective to detect both the seen and unseen anomalies. We propose a novel explicit boundary guided semi-push-pull contrastive learning mechanism, which can enhance model's discriminability while mitigating the bias issue. Our approach is based on two core designs: First, we find an explicit and compact separating boundary as the guidance for further feature learning. As the boundary only relies on the normal feature distribution, the bias problem caused by a few known anomalies can be alleviated. Second, a boundary guided semi-push-pull loss is developed to only pull the normal features together while pushing the abnormal features apart from the separating boundary beyond a certain margin region. In this way, our model can form a more explicit and discriminative decision boundary to distinguish known and also unseen anomalies from normal samples more effectively. Code will be available at https://github.com/xcyao00/BGAD.

cs.CV↗
arXiv2023

Liouville Theorem for Harmonic Maps from Riemannian Manifold with Compact Boundary

In this note we will provide a gradient estimate for harmonic maps from a complete noncompact Riemannian manifold with compact boundary (which we call "Kasue manifold") into a simply connected complete Riemannian manifold with non-positive sectional curvature. As a consequence, we can obtain a Liouville theorem. We will also show the nonexistence of positive solutions to some linear elliptic equation on Kasue manifold.

math.DG↗
arXiv2023

Guided Graph Generation: Evaluation of Graph Generators in Terms of Network Statistics, and a New Algorithm

We consider the problem of graph generation guided by network statistics, i.e., the generation of graphs which have given values of various numerical measures that characterize networks, such as the clustering coefficient and the number of cycles of given lengths. Algorithms for the generation of synthetic graphs are often based on graph growth models, i.e., rules of adding (and sometimes removing) nodes and edges to a graph that mimic the processes present in real-world networks. While such graph generators are desirable from a theoretical point of view, they are often only able to reproduce a narrow set of properties of real-world networks, resulting in graphs with otherwise unrealistic properties. In this article, we instead evaluate common graph generation algorithms at the task of reproducing the numerical statistics of real-world networks, such as the clustering coefficient, the degree assortativity, and the connectivity. We also propose an iterative algorithm, the Guided Graph Generator, based on a greedy-like procedure that recovers realistic values over a large number of commonly used graph statistics, while at the same time allowing an efficient implementation based on incremental updating of only a small number of subgraph counts. We show that the proposed algorithm outperforms previous graph generation algorithms in terms of the error in the reconstructed graphs for a large number of graph statistics such as the clustering coefficient, the assortativity, the mean node distance, and also evaluate the algorithm in terms of precision, speed of convergence and scalability, and compare it to previous graph generators and models. We also show that the proposed algorithm generates graphs with realistic degree distributions, graph spectra, clustering coefficient distributions, and distance distributions.

cs.SI↗
arXiv2023

SynGraphy: Succinct Summarisation of Large Networks via Small Synthetic Representative Graphs

We describe SynGraphy, a method for visually summarising the structure of large network datasets that works by drawing smaller graphs generated to have similar structural properties to the input graphs. Visualising complex networks is crucial to understand and make sense of networked data and the relationships it represents. Due to the large size of many networks, visualisation is extremely difficult; the simple method of drawing large networks like those of Facebook or Twitter leads to graphics that convey little or no information. While modern graph layout algorithms can scale computationally to large networks, their output tends to a common "hairball" look, which makes it difficult to even distinguish different graphs from each other. Graph sampling and graph coarsening techniques partially address these limitations but they are only able to preserve a subset of the properties of the original graphs. In this paper we take the problem of visualising large graphs from a novel perspective: we leave the original graph's nodes and edges behind, and instead summarise its properties such as the clustering coefficient and bipartivity by generating a completely new graph whose structural properties match that of the original graph. To verify the utility of this approach as compared to other graph visualisation algorithms, we perform an experimental evaluation in which we repeatedly asked experimental subjects (professionals in graph mining and related areas) to determine which of two given graphs has a given structural property and then assess which visualisation algorithm helped in identifying the correct answer. Our summarisation approach SynGraphy compares favourably to other techniques on a variety of networks.

cs.SI↗