相关论文: When and Where to Attack? Stage-wise Attention-Gui…

While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved…

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens…

Adversarial patch attacks pose a major threat to vision systems by embedding localized perturbations that mislead deep models. Traditional defense methods often require retraining or fine-tuning, making them impractical for real-world…

Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated concerning capabilities to generate harmful content when manipulated. While techniques like safety fine-tuning aim to minimize harmful use,…

This paper introduces a new method for adversarial attacks on large language models (LLMs) called the Single-Turn Crescendo Attack (STCA). Building on the multi-turn crescendo attack method introduced by Russinovich, Salem, and Eldan…

Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle…

In this paper, we investigate the dynamics-aware adversarial attack problem of adaptive neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

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…

Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches. However, both global perturbations and local patches…

Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly…

Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to backdoor…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…

Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks.…

The robustness of recent Large Language Models (LLMs) has become increasingly crucial as their applicability expands across various domains and real-world applications. Retrieval-Augmented Generation (RAG) is a promising solution for…

Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to a uniform pretraining resolution, often erasing fine-grained…

Advanced multimodal Retrieval-Augmented Generation (MRAG) techniques have been widely applied to enhance the capabilities of Large Multimodal Models (LMMs), but they also bring along novel safety issues. Existing adversarial research has…