Related papers: PoisonedParrot: Subtle Data Poisoning Attacks to E…

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…

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack…

The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs,…

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

The exposure of large language models (LLMs) to copyrighted material during pre-training raises concerns about unintentional copyright infringement post deployment. This has driven the development of "copyright takedown" methods,…

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

Deep learning (DL) models for natural language-to-code generation have become integral to modern software development pipelines. However, their heavy reliance on large amounts of data, often collected from unsanitized online sources,…

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose…

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on…

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…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into…

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks…