Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by human detection, limiting the effectiveness and practicality in real-world scenarios. To enhance the stealthiness of backdoor activation, we present a new poisoning paradigm against LLMs triggered by specifying generation conditions, which are commonly adopted strategies by users during model inference. The poisoned model performs normally for output under normal/other generation conditions, while becomes harmful for output under target generation conditions. To achieve this objective, we introduce BrieFool, an efficient attack framework. It leverages the characteristics of generation conditions by efficient instruction sampling and poisoning data generation, thereby influencing the behavior of LLMs under target conditions. Our attack can be generally divided into two types with different targets: Safety unalignment attack and Ability degradation attack. Our extensive experiments demonstrate that BrieFool is effective across safety domains and ability domains, achieving higher success rates than baseline methods, with 94.3 % on GPT-3.5-turbo
Code (0)
등록된 구현이 없습니다.
Tasks
Human DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Watch Your Steps: Local Image and Scene Editing by Text Instructions
Denoising diffusion models have enabled high-quality image generation and editing. We present a method to localize the desired edit region implicit in a text instruction. We leverage InstructPix2Pix (IP2P) and identify t…
DenoisingImage GenerationNeRFMake-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While …
Image GenerationVideo GenerationLearn to Guide Your Diffusion Model
Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates…
Image GenerationControlVAR: Exploring Controllable Visual Autoregressive Modeling
Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, h…
Image GenerationExploring Compositional Visual Generation with Latent Classifier Guidance
Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion model and classifier guidance in the late…
Image Generation