相关论文: Imperio: Language-Guided Backdoor Attacks for Arbi…

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks…

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…

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks…

Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack…

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…

This dissertation proposes a framework of user-centered security in Natural Language Processing (NLP), and demonstrates how it can improve the accessibility of related research. Accordingly, it focuses on two security domains within NLP…

Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs,…

The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate retraining models,…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

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…

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on…

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

We describe Panacea, a system that supports natural language processing (NLP) components for active defenses against social engineering attacks. We deploy a pipeline of human language technology, including Ask and Framing Detection, Named…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

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…