Related papers: Graph-Based Fuzz Testing for Deep Learning Inferen…

Fuzzing is a popular dynamic program analysis technique used to find vulnerabilities in complex software. Fuzzing involves presenting a target program with crafted malicious input designed to cause crashes, buffer overflows, memory errors,…

Fuzz testing is a fundamental technique employed to identify vulnerabilities within software systems. However, the process can be protracted and resource-intensive, especially when confronted with extensive codebases. In this work, I…

As Deep Learning (DL) models are increasingly applied in safety-critical domains, ensuring their quality has emerged as a pressing challenge in modern software engineering. Among emerging validation paradigms, coverage-guided testing (CGT)…

Deep Learning Systems (DLSs) have been widely applied in safety-critical tasks such as autopilot. However, when a perturbed input is fed into a DLS for inference, the DLS often has incorrect outputs (i.e., faults). DLS testing techniques…

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios.…

Fuzzing is an important dynamic program analysis technique designed for finding vulnerabilities in complex software. Fuzzing involves presenting a target program with crafted malicious input to cause crashes, buffer overflows, memory…

Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation…

Rigorous testing of machine learning models is necessary for trustworthy deployments. We present a novel black-box approach for generating test-suites for robust testing of deep neural networks (DNNs). Most existing methods create test…

Coverage-based graybox fuzzer (CGF), such as AFL has gained great success in vulnerability detection thanks to its ease-of-use and bug-finding power. Since some code fragments such as memory allocation are more vulnerable than others,…

Grey-box fuzz testing has revealed thousands of vulnerabilities in real-world software owing to its lightweight instrumentation, fast coverage feedback, and dynamic adjusting strategies. However, directly applying grey-box fuzzing to…

Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs, poses significant security risks.…

LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high benchmarks scores on SWE-bench, their API dependence, cost, and…

The control logic models built by Simulink or Ptolemy have been widely used in industry scenes. It is an urgent need to ensure the safety and security of the control logic models. Test case generation technologies are widely used to ensure…

Clinical diagnostic decision making and population-based studies often rely on multi-modal data which is noisy and incomplete. Recently, several works proposed geometric deep learning approaches to solve disease classification, by modeling…

Industrial equipment fault diagnosis often encounter challenges such as the scarcity of fault data, complex operating conditions, and varied types of failures. Signal analysis, data statistical learning, and conventional deep learning…

Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However,…

Dynamic fault trees (DFTs) have emerged as an important tool for capturing the dynamic behavior of system failure. These DFTs are then analyzed qualitatively and quantitatively using stochastic or algebraic methods to judge the failure…

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep…

Diffusion language models (DLMs) have recently emerged as a compelling alternative to autoregressive generation, offering parallel generation and improved global coherence. During inference, DLMs generate text by iteratively denoising…

Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited semantic awareness. Traditional greybox fuzzers rely on…