Harmful fine-tuning attacks and defenses for large language models: A survey
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 …
exposes serious safety concerns--fine-tuning over a few harmful data uploaded by the users …
Artwork protection against neural style transfer using locally adaptive adversarial color attack
Neural style transfer (NST) generates new images by combining the style of one image with
the content of another. However, unauthorized NST can exploit artwork, raising concerns …
the content of another. However, unauthorized NST can exploit artwork, raising concerns …
Clean-label backdoor attack and defense: An examination of language model vulnerability
Prompt-based learning, a paradigm that creates a bridge between pre-training and fine-
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
[HTML][HTML] On large language models safety, security, and privacy: A survey
R Zhang, HW Li, XY Qian, WB Jiang… - Journal of Electronic …, 2025 - Elsevier
The integration of artificial intelligence (AI) technology, particularly large language models
(LLMs), has become essential across various sectors due to their advanced language …
(LLMs), has become essential across various sectors due to their advanced language …
A grey-box attack against latent diffusion model-based image editing by posterior collapse
Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have
revolutionized image synthesis and manipulation. However, these generative techniques …
revolutionized image synthesis and manipulation. However, these generative techniques …
Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
The widespread adoption of deep learning across various industries has introduced
substantial challenges, particularly in terms of model explainability and security. The …
substantial challenges, particularly in terms of model explainability and security. The …
Quantized Delta Weight Is Safety Keeper
Recent advancements in fine-tuning proprietary language models enable customized
applications across various domains but also introduce two major challenges: high resource …
applications across various domains but also introduce two major challenges: high resource …
Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization
O Mengara - arXiv preprint arXiv:2407.14573, 2024 - arxiv.org
Since the advent of generative artificial intelligence, every company and researcher has
been rushing to develop their own generative models, whether commercial or not. Given the …
been rushing to develop their own generative models, whether commercial or not. Given the …
Exploring Potential Prompt Injection Attacks in Federated Military LLMs and Their Mitigation
Federated Learning (FL) is increasingly being adopted in military collaborations to develop
Large Language Models (LLMs) while preserving data sovereignty. However, prompt …
Large Language Models (LLMs) while preserving data sovereignty. However, prompt …
Towards effective neural topic modeling
X Wu - 2024 - dr.ntu.edu.sg
Over the past few decades, the world has witnessed an unprecedented explosion of
information. Of these, a substantial portion consists of unlabeled textual data, such as …
information. Of these, a substantial portion consists of unlabeled textual data, such as …