Recent research demonstrates that the nascent fine-tuning-as-a-service business model
exposes serious safety concerns--fine-tuning over a few harmful data uploaded by the users …

The advancement of Large Language Models (LLMs) has significantly impacted various
domains, including Web search, healthcare, and software development. However, as these …

Recent studies have shown that LLMs are vulnerable to denial-of-service (DoS) attacks,
where adversarial inputs like spelling errors or non-semantic prompts trigger endless …

With the continuous development of large language models (LLMs), transformer-based
models have made groundbreaking advances in numerous natural language processing …

The rapid advancement of large models, driven by their exceptional abilities in learning and
generalization through large-scale pre-training, has reshaped the landscape of Artificial …

Large Language Models (LLMs) are vulnerable to backdoor attacks, where hidden triggers
can maliciously manipulate model behavior. While several backdoor attack methods have …

Model editing methods modify specific behaviors of Large Language Models by altering a
small, targeted set of network weights and require very little data and compute. These …

With the rapid development of generative artificial intelligence, particularly large language
models, a number of sub-fields of deep learning have made significant progress and are …

This research investigates the effectiveness of established vulnerability metrics, such as the
Common Vulnerability Scoring System (CVSS), in evaluating attacks against Large …

We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt
(TIP) attacks. Our approach embeds sequence-to-sequence tasks (eg, cipher decoding …