paper-with-me

Papers

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models

2024-04-23 · Jiaming He, Wenbo Jiang, Guanyu Hou, Wenshu Fan, Rui Zhang, Hongwei Li

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

📄 PDF Abstract BibTeX arXiv:2404.14795

Code (0)

등록된 구현이 없습니다.

Tasks

Human Detection

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Watch Your Steps: Local Image and Scene Editing by Text Instructions

2023-08-17 · Ashkan Mirzaei, Tristan Aumentado-Armstrong, Marcus A. Brubaker, Jonathan Kelly 외

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 GenerationNeRF

Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance

2023-06-01 · Jinbo Xing, Menghan Xia, Yuxin Liu, Yuechen Zhang 외

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 Generation

Learn to Guide Your Diffusion Model

2025-10-01 · Alexandre Galashov, Ashwini Pokle, Arnaud Doucet, Arthur Gretton 외 arxiv

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 Generation

ControlVAR: Exploring Controllable Visual Autoregressive Modeling

2024-06-14 · Xiang Li, Kai Qiu, Hao Chen, Jason Kuen 외

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 Generation

Exploring Compositional Visual Generation with Latent Classifier Guidance

2023-04-25 · Changhao Shi, Haomiao Ni, Kai Li, Shaobo Han 외

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