Related papers: PBFuzz: Agentic Directed Fuzzing for PoV Generatio…
Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I…
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…
Deep learning (DL) systems can make our life much easier, and thus are gaining more and more attention from both academia and industry. Meanwhile, bugs in DL systems can be disastrous, and can even threaten human lives in safety-critical…
As blockchain platforms grow exponentially, millions of lines of smart contract code are being deployed to manage extensive digital assets. However, vulnerabilities in this mission-critical code have led to significant exploitations and…
Fuzzing is a powerful software testing technique renowned for its effectiveness in identifying software vulnerabilities. Traditional fuzzing evaluations typically focus on overall fuzzer performance across a set of target programs, yet few…
While recent approaches leverage large language models (LLMs) and multi-agent pipelines to automatically generate proof-of-concept (PoC) exploits from vulnerability reports, existing systems often suffer from two fundamental limitations:…
Taint-style vulnerabilities comprise a majority of fuzzer discovered program faults. These vulnerabilities usually manifest as memory access violations caused by tainted program input. Although fuzzers have helped uncover a majority of…
The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language…
Fuzz Testing techniques are the state of the art in software testing for security issues nowadays. Their great effectiveness attracted the attention of researchers and hackers and involved them in developing a lot of new techniques to…
Large language models (LLMs) have made rapid advancements in code generation for popular languages such as Python and C++. Many of these recent gains can be attributed to the use of ``agents'' that wrap domain-relevant tools alongside LLMs.…
Fuzzing is a widely used technique for detecting vulnerabilities in smart contracts, which generates transaction sequences to explore the execution paths of smart contracts. However, existing fuzzers are falling short in detecting…
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…
The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…
The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool…
Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attention of research communities. While model owners can defend…
Fuzzing is a widely used technique for detecting software bugs and vulnerabilities. Most popular fuzzers generate new inputs using an evolutionary search to maximize code coverage. Essentially, these fuzzers start with a set of seed inputs,…
Ensuring the correctness of compiler optimizations is critical, but existing fuzzers struggle to test optimizations effectively. First, most fuzzers use optimization pipelines (heuristics-based, fixed sequences of passes) as their harness.…
As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software…
The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these…
Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacterized. We present PromptAudit, a controlled evaluation framework that isolates prompt…