Related papers: ExpGuard: LLM Content Moderation in Specialized Do…

The rapid adoption of open-source Large Language Models (LLMs) in offline and enterprise environments has introduced a largely unexamined security risk like susceptibility to adversarial phishing prompts under static safety configurations.…

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Recent advancements in Text-to-Image (T2I) models have raised significant safety concerns about their potential misuse for generating inappropriate or Not-Safe-For-Work (NSFW) contents, despite existing countermeasures such as NSFW…

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited digital literacy, and cognitive decline, yet existing…

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful and benign prompts.…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on fragile handcrafted rules or data-driven features that fail to capture evolving attack semantics.…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…

High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk…

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…

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but…

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors.…