相关论文: When Understanding Becomes a Risk: Authenticity an…

Existing large language models (LLMs) are advancing rapidly and produce outstanding results in image generation tasks, yet their content safety checks remain vulnerable to prompt-based jailbreaks. Through preliminary testing on platforms…

Automated disinformation generation is often listed as an important risk associated with large language models (LLMs). The theoretical ability to flood the information space with disinformation content might have dramatic consequences for…

Recent research has highlighted the risk of generative model collapse, where performance progressively degrades when continually trained on self-generated data. However, existing exploration on model collapse is limited to single, unimodal…

Large Language Models (LLMs) are increasingly embedded in child-facing contexts such as education, companionship, creative tools, but their deployment raises safety, privacy, developmental, and security risks. We conduct a systematic…

This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…

The rapid advancement of Large Language Models (LLMs) has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code…

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding their safe operations from multiple aspects, e.g., truthfulness, robustness, and fairness.…

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate…

Fashionable image generation aims to synthesize images of diverse fashion prevalent around the globe, helping fashion designers in real-time visualization by giving them a basic customized structure of how a specific design preference would…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity fraud. Existing detection methods identify morphed images…

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counterintuitive phenomenon that using textual unlearning to align MLLMs…

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…

Large language models (LLMs) often generate inaccurate yet credible-sounding content, known as hallucinations. This inherent feature of LLMs poses significant risks, especially in critical domains. I analyze LLMs as a new class of…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically…

Large language models (LLMs) have achieved record adoption in a short period of time across many different sectors including high importance areas such as education [4] and healthcare [23]. LLMs are open-ended models trained on diverse data…