Related papers: Continuous Discovery of Vulnerabilities in LLM Ser…

Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of vulnerabilities that only manifest under specific option-input combinations. Prior works of CLI…

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory…

Fuzzing has been incredibly successful in uncovering bugs and vulnerabilities across diverse software systems. JSON parsers play a vital role in modern software development, and ensuring their reliability is of great importance. This…

Context: Exhaustive fuzzing of modern JavaScript engines is infeasible due to the vast number of program states and execution paths. Coverage-guided fuzzers waste effort on low-risk inputs, often ignoring vulnerability-triggering ones that…

Multi-Agent LLM Systems (MAS) have been adopted to automate complex human workflows by breaking down tasks into subtasks. However, due to the non-deterministic behavior of LLM agents and the intricate interactions between agents, MAS…

Fuzzing is a well-established technique for detecting bugs and vulnerabilities. With the surge of fuzzers and fuzzer platforms being developed such as AFL and OSSFuzz rises the necessity to benchmark these tools' performance. A common…

In the past decade, Deep Learning (DL) systems have been widely deployed in various domains to facilitate our daily life. Meanwhile, it is extremely challenging to ensure the correctness of DL systems (e.g., due to their intrinsic…

Software's pervasive impact and increasing reliance in the era of digital transformation raise concerns about vulnerabilities, emphasizing the need for software security. Fuzzy testing is a dynamic analysis software testing technique that…

The recent advances in LLMs bring a strong demand for efficient system support to improve overall serving efficiency. As LLM inference scales towards multiple GPUs and even multiple compute nodes, various coordination patterns, such as…

Smart contracts play a pivotal role in blockchain ecosystems, and fuzzing remains an important approach to securing smart contracts. Even though mutation scheduling is a key factor influencing fuzzing effectiveness, existing fuzzers have…

Autoregressive inference in large transformer-based language models (LLMs) presents significant challenges for runtime efficiency, particularly during the decode phase where load imbalance across GPU shards can cause throughput degradation…

Developers utilize third-party libraries to improve productivity, which also introduces potential security risks. Existing approaches generate tests for public functions to trigger library vulnerabilities from client programs, yet they…

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a…

As mobile networks transition to 5G infrastructure, ensuring robust security becomes more important due to the complex architecture and expanded attack surface. Traditional security testing approaches for 5G networks rely on black-box…

The Operating System (OS) kernel is foundational in modern computing, especially with the proliferation of diverse computing devices. However, its development also comes with vulnerabilities that can lead to severe security breaches. Kernel…

This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic foundations. Despite rapid advances in serving systems such as vLLM and SGLang, their…

Integration of machine learning (ML) in 5G-based Internet of Vehicles (IoV) networks has enabled intelligent transportation and smart traffic management. Nonetheless, the security against adversarial poisoning attacks is also increasingly…

Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challenging due to the need for satisfying both language…

Autonomous vehicles (AVs) are more vulnerable to network attacks due to the high connectivity and diverse communication modes between vehicles and external networks. Deep learning-based Intrusion detection, an effective method for detecting…

In the past few years, several attacks against the vulnerabilities of EOSIO smart contracts have caused severe financial losses to this prevalent blockchain platform. As a lightweight test-generation approach, grey-box fuzzing can open up…