Yu Jiang

Qifang Zhao, Tianyu Li, Meng Du et al.

When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost. We present a unified user-item matching framework to simultaneously conduct item recommendation and user targeting with just one model. We empirically demonstrate that the above concurrent modeling is viable via modeling the user-item interaction matrix with the multinomial distribution, and propose a bidirectional bias-corrected NCE loss for the implementation. The proposed loss function guides the model to learn the user-item joint probability $p(u,i)$ instead of the conditional probability $p(i|u)$ or $p(u|i)$ through correcting both the users and items' biases caused by the in-batch negative sampling. In addition, our framework is model-agnostic enabling a flexible adaptation of different model architectures. Extensive experiments demonstrate that our framework results in significant performance gains in comparison with the state-of-the-art methods, with greatly reduced cost on computing resources and daily maintenance.

Yuanliang Chen, Yu Jiang, Fuchen Ma et al.

Fuzzing is widely used for software vulnerability detection. There are various kinds of fuzzers with different fuzzing strategies, and most of them perform well on their targets. However, in industry practice and empirical study, the performance and generalization ability of those well-designed fuzzing strategies are challenged by the complexity and diversity of real-world applications. In this paper, inspired by the idea of ensemble learning, we first propose an ensemble fuzzing approach EnFuzz, that integrates multiple fuzzing strategies to obtain better performance and generalization ability than that of any constituent fuzzer alone. First, we define the diversity of the base fuzzers and choose those most recent and well-designed fuzzers as base fuzzers. Then, EnFuzz ensembles those base fuzzers with seed synchronization and result integration mechanisms. For evaluation, we implement EnFuzz , a prototype basing on four strong open-source fuzzers (AFL, AFLFast, AFLGo, FairFuzz), and test them on Google's fuzzing test suite, which consists of widely used real-world applications. The 24-hour experiment indicates that, with the same resources usage, these four base fuzzers perform variously on different applications, while EnFuzz shows better generalization ability and always outperforms others in terms of path coverage, branch coverage and crash discovery. Even compared with the best cases of AFL, AFLFast, AFLGo and FairFuzz, EnFuzz discovers 26.8%, 117%, 38.8% and 39.5% more unique crashes, executes 9.16%, 39.2%, 19.9% and 20.0% more paths and covers 5.96%, 12.0%, 21.4% and 11.1% more branches respectively.

Quan Zhang, Binqi Zeng, Chijin Zhou et al.

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG) technique. However, these frameworks' designs do not have sufficient consideration of the risk of external content, thereby allowing attackers to undermine the applications developed with these frameworks. In this paper, we reveal a new threat to LLM-powered applications, termed retrieval poisoning, where attackers can guide the application to yield malicious responses during the RAG process. Specifically, through the analysis of LLM application frameworks, attackers can craft documents visually indistinguishable from benign ones. Despite the documents providing correct information, once they are used as reference sources for RAG, the application is misled into generating incorrect responses. Our preliminary experiments indicate that attackers can mislead LLMs with an 88.33\% success rate, and achieve a 66.67\% success rate in the real-world application, demonstrating the potential impact of retrieval poisoning.

Yu Jiang, Jie Liang, Fuchen Ma et al.

Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. In this paper, we identified five major challenges of LLM-assisted fuzzing. To support our findings, we revisited the most recent papers from top-tier conferences, confirming that these challenges are widespread. As a remedy, we propose some actionable recommendations to help improve applying LLM in Fuzzing and conduct preliminary evaluations on DBMS fuzzing. The results demonstrate that our recommendations effectively address the identified challenges.

Dongning Ma, Jianmin Guo, Yu Jiang et al.

Brain-inspired hyperdimensional computing (HDC) is an emerging computational paradigm that mimics brain cognition and leverages hyperdimensional vectors with fully distributed holographic representation and (pseudo)randomness. Compared to other machine learning (ML) methods such as deep neural networks (DNNs), HDC offers several advantages including high energy efficiency, low latency, and one-shot learning, making it a promising alternative candidate on a wide range of applications. However, the reliability and robustness of HDC models have not been explored yet. In this paper, we design, implement, and evaluate HDTest to test HDC model by automatically exposing unexpected or incorrect behaviors under rare inputs. The core idea of HDTest is based on guided differential fuzz testing. Guided by the distance between query hypervector and reference hypervector in HDC, HDTest continuously mutates original inputs to generate new inputs that can trigger incorrect behaviors of HDC model. Compared to traditional ML testing methods, HDTest does not need to manually label the original input. Using handwritten digit classification as an example, we show that HDTest can generate thousands of adversarial inputs with negligible perturbations that can successfully fool HDC models. On average, HDTest can generate around 400 adversarial inputs within one minute running on a commodity computer. Finally, by using the HDTest-generated inputs to retrain HDC models, we can strengthen the robustness of HDC models. To the best of our knowledge, this paper presents the first effort in systematically testing this emerging brain-inspired computational model.

Mingzhe Wang, Zhiyong Wu, Xinyi Xu et al.

As an infrastructure for data persistence and analysis, Database Management Systems (DBMSs) are the cornerstones of modern enterprise software. To improve their correctness, the industry has been applying blackbox fuzzing for decades. Recently, the research community achieved impressive fuzzing gains using coverage guidance. However, due to the complexity and distributed nature of enterprise-level DBMSs, seldom are these researches applied to the industry. In this paper, we apply coverage-guided fuzzing to enterprise-level DBMSs from Huawei and Bloomberg LP. In our practice of testing GaussDB and Comdb2, we found major challenges in all three testing stages. The challenges are collecting precise coverage, optimizing fuzzing performance, and analyzing root causes. In search of a general method to overcome these challenges, we propose Ratel, a coverage-guided fuzzer for enterprise-level DBMSs. With its industry-oriented design, Ratel improves the feedback precision, enhances the robustness of input generation, and performs an on-line investigation on the root cause of bugs. As a result, Ratel outperformed other fuzzers in terms of coverage and bugs. Compared to industrial black box fuzzers SQLsmith and SQLancer, as well as coverage-guided academic fuzzer Squirrel, Ratel covered 38.38%, 106.14%, 583.05% more basic blocks than the best results of other three fuzzers in GaussDB, PostgreSQL, and Comdb2, respectively. More importantly, Ratel has discovered 32, 42, and 5 unknown bugs in GaussDB, Comdb2, and PostgreSQL.

Jiyuan Wang, Ming Gao, Yu Jiang et al.

Nowadays, quantum program is widely used and quickly developed. However, the absence of testing methodology restricts their quality. Different input format and operator from traditional program make this issue hard to resolve. In this paper, we present QuanFuzz, a search-based test input generator for quantum program. We define the quantum sensitive information to evaluate test input for quantum program and use matrix generator to generate test cases with higher coverage. First, we extract quantum sensitive information -- measurement operations on those quantum registers and the sensitive branches associated with those measurement results, from the quantum source code. Then, we use the sensitive information guided algorithm to mutate the initial input matrix and select those matrices which improve the probability weight for a value of the quantum register to trigger the sensitive branch. The process keeps iterating until the sensitive branch triggered. We tested QuanFuzz on benchmarks and acquired 20% - 60% more coverage compared to traditional testing input generation.

Jianmin Guo, Yu Jiang, Yue Zhao et al.

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always fail to include rare inputs in the testing dataset and exhibit low neuron coverage. In this paper, we propose DLFuzz, the frst differential fuzzing testing framework to guide DL systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other DL systems with the same functionality. We present empirical evaluations on two well-known datasets to demonstrate its efficiency. Compared with DeepXplore, the state-of-the-art DL whitebox testing framework, DLFuzz does not require extra efforts to find similar functional DL systems for cross-referencing check, but could generate 338.59% more adversarial inputs with 89.82% smaller perturbations, averagely obtain 2.86% higher neuron coverage, and save 20.11% time consumption.

Mohammad Hosseini, Yu Jiang, Richard R. Berlin et al.

The ultimate objective of medical cyber-physical systems is to enhance the safety and effectiveness of patient care. To ensure safe and effective care during emergency patient transfer from rural areas to center tertiary hospitals, reliable and real-time communication is essential. Unfortunately, real-time monitoring of patients involves transmission of various clinical multimedia data including videos, medical images, and vital signs, which requires use of mobile network with high-fidelity communication bandwidth. However, the wireless networks along the roads in rural areas range from 4G to 2G to low speed satellite links, which poses a significant challenge to transmit critical patient information. In this paper, we present a bandwidth-compliant criticality-aware system for transmission of massive clinical multimedia data adaptive to varying bandwidths during patient transport. Model-based clinical automata are used to determine the criticality of clinical multimedia data. We borrow concepts from DASH, and propose physiology-aware adaptation techniques to transmit more critical clinical data with higher fidelity in response to changes in disease, clinical states, and bandwidth condition. In collaboration with Carle's ambulance service center, we develop a bandwidth profiler, and use it as proof of concept to support our experiments. Our preliminary evaluation results show that our solutions ensure that most critical patient's clinical data are communicated with higher fidelity.