相关论文: Alignment Drift in Multimodal LLMs: A Two-Phase, L…

Multimodal large language models (MLLMs) are increasingly used in real world applications, yet their safety under adversarial conditions remains underexplored. This study evaluates the harmlessness of four leading MLLMs (GPT-4o, Claude…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and vision, yet whether these advances translate into…

Vision Large Language Models (VLLMs) represent a significant advancement in artificial intelligence by integrating image-processing capabilities with textual understanding, thereby enhancing user interactions and expanding application…

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on their specific versions, overlooking the impact of…

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

The recent emergence of multimodal large language models (LLMs) has introduced new opportunities for improving visual hazard recognition on construction sites. Unlike traditional computer vision models that rely on domain-specific training…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single prompts; however,…

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like…

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses. While…

Large language models (LLMs) are now deployed at unprecedented scale, assisting millions of users in daily tasks. However, the risk of these models assisting unlawful activities remains underexplored. In this study, we define this high-risk…

This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against diverse adversarial attack vectors. We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack…