相关论文: Universal Acoustic Adversarial Attacks for Flexibl…

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial…

Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their…

This paper investigates the real-world vulnerabilities of audio-based large language models (ALLMs), such as Qwen2-Audio. We first demonstrate that an adversary can craft stealthy audio perturbations to manipulate ALLMs into exhibiting…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied…

Large Language Models (LLMs) have become vital tools in software development tasks such as code generation, completion, and analysis. As their integration into workflows deepens, ensuring robustness against vulnerabilities especially those…

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more…

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…