Related papers: Unveiling Vulnerability of Self-Attention
Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…
The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…
Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…
Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…
Prompt-based learning has been proved to be an effective way in pre-trained language models (PLMs), especially in low-resource scenarios like few-shot settings. However, the trustworthiness of PLMs is of paramount significance and potential…
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data. However, these models can lead to system failure or undesirable outputs when being exposed to spoken language…
Large Language Models (LLMs) show remarkable semantic understanding but often struggle with structural understanding when processing graph topologies in a serialized format. Existing solutions rely on training external graph-based adapters…
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…
Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…
Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…
In-context learning is a remarkable property of transformers and has been the focus of recent research. An attention mechanism is a key component in transformers, in which an attention matrix encodes relationships between words in a…
The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…
Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will…
Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing…
Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…
Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…
Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially…