相关论文: Why does weak-OOD help? A Further Step Towards Und…

The reliability of artificial intelligence (AI) systems in open-world settings depends heavily on their ability to flag out-of-distribution (OOD) inputs unseen during training. Recent advances in large-scale vision-language models (VLMs)…

Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of…

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting OOD examples work well when evaluated on benign in-distribution and OOD samples. However,…

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications. While there has been a growing focus on OOD detection in visual data, the field of textual OOD…

Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental…

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…

Deep neural networks have found widespread adoption in solving complex tasks ranging from image recognition to natural language processing. However, these networks make confident mispredictions when presented with data that does not belong…

Detecting out-of-distribution (OOD) instances is significant for the safe deployment of NLP models. Among recent textual OOD detection works based on pretrained language models (PLMs), distance-based methods have shown superior performance.…

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and…

Out-of-Distribution (OOD) detection is critical for safe deployment; however, existing detectors often struggle to generalize across datasets of varying scales and model architectures, and some can incur high computational costs in…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…

Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection…

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such…

This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different from prior studies, we shift our focus from evaluating standard performance to introducing a comprehensive safety evaluation suite, covering both…

Out-of-distribution (OOD) detection, i.e., finding test samples derived from a different distribution than the training set, as well as reasoning about such samples (OOD reasoning), are necessary to ensure the safety of results generated by…

Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs)…