Related papers: Opir: Efficient Multi-Task Safety Classification f…
Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the…
With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies. Current…
The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…
Classification is one of the most widespread tasks in AI applications, serving often as the first step in filtering, sorting, and categorizing data. Since modern AI systems must handle large volumes of input data and early pipeline stages…
Large Reasoning Models (LRMs) have recently extended their powerful reasoning capabilities to safety checks-using chain-of-thought reasoning to decide whether a request should be answered. While this new approach offers a promising route…
Existing backdoor defense methods are only effective for limited trigger types. To defend different trigger types at once, we start from the class-irrelevant nature of the poisoning process and propose a novel weakly supervised backdoor…
The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with…
Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…
Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…
Powered by remarkable advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks. However, the practical application scenarios of MLLMs are intricate,…
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models…
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…
Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…
Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation…
Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…
Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…
Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…
Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with…
Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…
In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…