Related papers: Backdooring Vision-Language Models with Out-Of-Dis…

Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional…

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating…

Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task-oriented dialogue (TOD) systems. Previous methods address…

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack…

In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning…

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area…

Vision-Language Models (VLMs) represent a significant breakthrough in artificial intelligence by integrating visual and textual modalities to achieve impressive zero-shot capabilities. However, VLMs are susceptible to catastrophic…

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as text. LMs have a wide range of applications in natural language…

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their…

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…