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

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.…

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…

Detecting anomalies or out-of-distribution (OOD) samples is critical for maintaining the reliability and trustworthiness of machine learning systems. Recently, Large Language Models (LLMs) have demonstrated their effectiveness not only in…

In trustworthy medical diagnosis systems, integrating out-of-distribution (OOD) detection aims to identify unknown diseases in samples, thereby mitigating the risk of misdiagnosis. In this study, we propose a novel OOD detection framework…

The adaptation of large-scale Vision-Language Models (VLMs) through post-training reveals a pronounced generalization gap: models fine-tuned with Reinforcement Learning (RL) consistently achieve superior out-of-distribution (OOD)…

The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our…

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success…

Detecting out-of-distribution (OOD) data is a fundamental challenge in the deployment of machine learning models. From a security standpoint, this is particularly important because OOD test data can result in misleadingly confident yet…

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world…

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…