相关论文: Test-time Backdoor Mitigation for Black-Box Large …

In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a critical vulnerability to backdoor attacks, where adversaries can…

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Generative large language models are crucial in natural language processing, but they are vulnerable to backdoor attacks, where subtle triggers compromise their behavior. Although backdoor attacks against LLMs are constantly emerging,…