相关论文: SmoothGuard: Defending Multimodal Large Language M…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial attacks. This paper…

Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges.…

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse…

The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks. However, the vast potential and remarkable capabilities of LLMs also raise new security and privacy concerns if they are…

Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare…

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.…

As Large Language Models (LLMs) increasingly permeate human life, their security has emerged as a critical concern, particularly their ability to maintain harmless responses to malicious instructions. Although extensive methods have…

Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational…

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited,…

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component,…

Large Language Models (LLMs) hold promise for advancing legal practice by automating complex tasks and improving access to justice. However, their adoption is limited by concerns over client confidentiality, especially when lawyers include…

Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current safeguards. We introduce SACRED-Bench (Speech-Audio…

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are…

Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially…

Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge…

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the…

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context…