相关论文: Unveiling Vulnerability of Self-Attention

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

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…

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking…

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

Transformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attention mechanism, a direct method is to visualize the attention…

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult…

Although large language models (LLMs) have achieved significant success in natural language processing, they still struggle with long-context comprehension. Traditional approaches to mitigating this issue typically rely on fine-tuning or…

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics. Our likelihood-guided text perturbations reveal a correlation between token likelihood…

Large Language Models (LLMs), already shown to ace various unstructured text comprehension tasks, have also remarkably been shown to tackle table (structured) comprehension tasks without specific training. Building on earlier studies of…