PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
원문 초록
As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding LLM-generated content, addressing copyright infringement remains a significant challenge. In this paper, we introduce PoisonedParrot: the first stealthy data poisoning attack that induces an LLM to generate copyrighted content even when the model has not been directly trained on the specific copyrighted material. PoisonedParrot integrates small fragments of copyrighted text into the poison samples using an off-the-shelf LLM. Despite its simplicity, evaluated in a wide range of experiments, PoisonedParrot is surprisingly effective at priming the model to generate copyrighted content with no discernible side effects. Moreover, we discover that existing defenses are largely ineffective against our attack. Finally, we make the first attempt at mitigating copyright-infringement poisoning attacks by proposing a defense: ParrotTrap. We encourage the community to explore this emerging threat model further.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
VLMs Can Aggregate Scattered Training Patches
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Images
Data Poisoning in Deep Learning: A Survey
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.