相关论文: Virus: Harmful Fine-tuning Attack for Large Langua…

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

Generative AI systems powered by Large Language Models (LLMs) usually use content moderation to prevent harmful content spread. To evaluate the robustness of content moderation, several metamorphic testing techniques have been proposed to…

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to generating harmful content when exposed to unsafe queries raises…

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

This research addresses the complex challenge of automated repair of code vulnerabilities, vital for enhancing digital security in an increasingly technology-driven world. The study introduces a novel and efficient format for the…

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

Large Language Models (LLMs) have transformed software development and automated code generation. Motivated by these advancements, this paper explores the feasibility of LLMs in modifying malware source code to generate variants. We…

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model. We conduct an empirical…

The risks derived from large language models (LLMs) generating deceptive and damaging content have been the subject of considerable research, but even safe generations can lead to problematic downstream impacts. In our study, we shift the…