相关论文: SpellBound: Defending Against Package Typosquattin…

As the default package manager for Node.js, npm has become one of the largest package management systems in the world. To facilitate dependency management for developers, npm supports a special type of dependency, Peer Dependency, whose…

Large language models (LLMs) have witnessed a meteoric rise in popularity among the general public users over the past few months, facilitating diverse downstream tasks with human-level accuracy and proficiency. Prompts play an essential…

Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. This paper identifies a new, prevalent hardware supply-chain attack surface that can bypass multiprocessor secure boot due…

The NPM ecosystem has become a primary target for software supply chain attacks, yet existing detection tools are evaluated in isolation on incompatible datasets, making cross-tool comparison unreliable. We conduct a benchmark-driven…

Recently, large language models (LLMs) have garnered widespread attention for their exceptional capabilities. Prompts are central to the functionality and performance of LLMs, making them highly valuable assets. The increasing reliance on…

In Go, the widespread adoption of open-source software has led to a flourishing ecosystem of third-party dependencies, which are often integrated into critical systems. However, the reuse of dependencies introduces significant supply chain…

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…

The disconnect between distributed software artifacts and their supposed source code enables attackers to leverage the build process for inserting malicious functionality. Past research in this field focuses on compiled language ecosystems,…

To counter man-at-the-end attacks such as reverse engineering and tampering, software is often protected with techniques that require support modules to be linked into the application. It is well-known, however, that attackers can exploit…

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Different security issues are a common problem for open source packages archived to and delivered through software ecosystems. These often manifest themselves as software weaknesses that may lead to concrete software vulnerabilities. This…

Modern software design practice implies widespread use in the development of ready-made components, usually designed as external libraries. The undoubted advantages of reusing third-party code can be offset by integration errors that appear…

Background. From information theory, surprisal is a measurement of how unexpected an event is. Statistical language models provide a probabilistic approximation of natural languages, and because surprisal is constructed with the probability…

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Web application pentesting is a crucial component in the offensive cybersecurity area, whose aim is to safeguard web applications and web services as the majority of the web applications are mounted in publicly accessible web environments.…

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…

Managing project dependencies is a key maintenance issue in software development. Developers need to choose an update strategy that allows them to receive important updates and fixes while protecting them from breaking changes. Semantic…

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

Text-to-image (T2I) models can be maliciously used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. Previous attacks largely depend on the availability of the diffusion…