相关论文: Legion: Best-First Concolic Testing

Recent advances in large language models (LLMs) have significantly impacted the domain of multi-hop question answering (MHQA), where systems are required to aggregate information and infer answers from disparate pieces of text. However, the…

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…

Concolic testing is a test generation technique which works effectively by integrating random testing generation and symbolic execution. Existing concolic testing engines focus on numeric programs. Heap-manipulating programs make extensive…

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,…

Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of…

In a Federated Learning (FL) setup, a number of devices contribute to the training of a common model. We present a method for selecting the devices that provide updates in order to achieve improved generalization, fast convergence, and…

Patch fuzzing is a technique aimed at identifying vulnerabilities that arise from newly patched code. While researchers have made efforts to apply patch fuzzing to testing JavaScript engines with considerable success, these efforts have…

Software fuzzing is a strong testing technique that has become the de facto approach for automated software testing and software vulnerability detection in the industry. The random nature of fuzzing makes monitoring and understanding the…

Monte Carlo Tree Search (MCTS) is an effective test-time compute scaling (TTCS) method for improving the reasoning performance of large language models, but its highly variable execution time leads to severe long-tail latency in practice.…

AlphaZero and its extension MuZero are computer programs that use machine-learning techniques to play at a superhuman level in chess, go, and a few other games. They achieved this level of play solely with reinforcement learning from…

Fuzzing is an important method to discover vulnerabilities in programs. Despite considerable progress in this area in the past years, measuring and comparing the effectiveness of fuzzers is still an open research question. In software…

Monte Carlo Tree Search (MCTS) is a sampling best-first method to search for optimal decisions. The success of MCTS depends heavily on how the MCTS statistical tree is built and the selection policy plays a fundamental role in this. A…

Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we formalise…

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…

We present THOUGHTSCULPT, a general reasoning and search method for tasks with outputs that can be decomposed into components. THOUGHTSCULPT explores a search tree of potential solutions using Monte Carlo Tree Search (MCTS), building…

In this work we study a well-known and challenging problem of Multi-agent Pathfinding, when a set of agents is confined to a graph, each agent is assigned a unique start and goal vertices and the task is to find a set of collision-free…

Hardware security vulnerabilities in computing systems compromise the security defenses of not only the hardware but also the software running on it. Recent research has shown that hardware fuzzing is a promising technique to efficiently…

Long-horizon robot manipulation tasks remain challenging for Vision-Language-Action (VLA) policies due to drift and exposure bias, often denoise the entire trajectory with fixed hyperparameters, causing small geometric errors to compound…

Existing LLM-based compiler fuzzers often produce syntactically or semantically invalid test programs, limiting their effectiveness in exercising compiler optimizations and backend components. We introduce ReFuzzer, a framework for refining…

Motivation: Engineering high-affinity binders targeting specific antigenic determinants remains a challenging and often daunting task, requiring extensive experimental screening. Computational methods have the potential to accelerate this…