Related papers: Debootstrapping without Archeology: Stacked Implem…

Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability detection. While compiler optimizations and third-party code often introduce transformations that…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

We introduce PPBoot: a bootstrap-based method for prediction-powered inference. PPBoot is applicable to arbitrary estimation problems and is very simple to implement, essentially only requiring one application of the bootstrap. Through a…

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Albeit being a central notion of every programming language, formally and modularly reasoning about iteration proves itself to be a non-trivial feat, specially in the context of higher-order iteration. In this paper, we present a generic…

Context: Refactoring is the art of modifying the design of a system without altering its behavior. The idea is to reorganize variables, classes and methods to facilitate their future adaptations and comprehension. As the concept of behavior…

Fault localization has been determined as a major resource factor in the software development life cycle. Academic fault localization techniques are mostly unknown and unused in professional environments. Although manual debugging…

Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally lack the capability for continuous learning and self-evolution from interactions, limiting the…

The strength of obfuscated software has increased over the recent years. Compiler based obfuscation has become the de facto standard in the industry and recent papers also show that injection of obfuscation techniques is done at the…

In this paper, we provide a comprehensive, hands-on tutorial on how to apply deductive verification to programs written in OCaml. In particular, we show how one can use the GOSPEL specification language and the Cameleer tool to conduct…

Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to…

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a…

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to…

Much software, whether beneficent or malevolent, is distributed only as binaries, sans source code. Absent source code, understanding binaries' behavior can be quite challenging, especially when compiled under higher levels of compiler…

Detecting vulnerability fix commits in open-source software is crucial for maintaining software security. To help OSS identify vulnerability fix commits, several automated approaches are developed. However, existing approaches like…

Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Language Model (LLM) applications, especially chatbots.…

Using automated reasoning, code synthesis, and contextual decision-making, we introduce a new threat that exploits large language models (LLMs) to autonomously plan, adapt, and execute the ransomware attack lifecycle. Ransomware 3.0…

Large Language Models (LLMs) can solve previously intractable tasks given only natural-language instructions and a few examples, but they remain difficult to steer precisely and lack a key capability for building reliable software at scale:…

Code retrieval helps developers reuse the code snippet in the open-source projects. Given a natural language description, code retrieval aims to search for the most relevant code among a set of code. Existing state-of-the-art approaches…

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…