Related papers: Poisoning Programs by Un-Repairing Code: Security …

With generative AI becoming widespread, the existence of AI-based programming assistants for developers is no surprise. Developers increasingly use them for their work, including generating code to fulfil the data protection requirements…

As artificial intelligence becomes increasingly integrated into software development processes, the prevalence and sophistication of AI-generated code continue to expand rapidly. This study addresses the critical need for transparency and…

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…

Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code repositories, to suggest likely (not just statically…

The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…

Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model…

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

The rapid adoption of Large Language Models(LLMs) for code generation has transformed software development, yet little attention has been given to how security vulnerabilities evolve through iterative LLM feedback. This paper analyzes…

With the ongoing rapid adoption of Artificial Intelligence (AI)-based systems in high-stakes domains, ensuring the trustworthiness, safety, and observability of these systems has become crucial. It is essential to evaluate and monitor AI…

Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight attack scenarios in four categories: architectural attacks on convolutional neural…

Generative AI enables rapid ``vibe coding," where natural language prompts yield working software systems. While this lowers barriers to software creation, it also collapses the boundary between prototypes and engineered software, leading…

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a boost in productivity. However, researchers have recently…

The rapid advancement of Large Language Models (LLMs) has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code…

The computing education community has a rich history of pedagogical innovation designed to support students in introductory courses, and to support teachers in facilitating student learning. Very recent advances in artificial intelligence…

In this paper, we consider contamination by code generation test sets, in particular in their use in modern large language models. We discuss three possible sources of such contamination and show findings supporting each of them: (i) direct…

Machine learning (ML) and artificial intelligence (AI) techniques have now become commonplace in software products and services. When threat modelling a system, it is therefore important that we consider threats unique to ML and AI…

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks…