相关论文: Speech-Audio Compositional Attacks on Multimodal L…

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,…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…

The rise of Omni-modal Large Language Models (OLLMs), which integrate visual and auditory processing with text, necessitates robust safety evaluations to mitigate harmful outputs. However, no dedicated benchmarks currently exist for OLLMs,…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current benchmarks primarily concentrate on single-turn dialogues or a single jailbreak attack method…

With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spelling variations, multiple languages, different scripts, and a…

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing formal guarantees for such models is hard because "harmful…

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are more efficient and often excel at specific tasks. This…

As large language models (LLMs) become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack…

Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate reliably in the presence of malicious adversaries. While recent benchmarks have evaluated large…

Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our…