6 papers
EmbTracker: Traceable Black-box Watermarking for Federated Language Models
Haodong Zhao, Jinming Hu, Yijie Bai +6
Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the re…
PINA: Prompt Injection Attack against Navigation Agents
Jiani Liu, Yixin He, Lanlan Fan +5
Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their securi…
Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
Yinan Zhong, Qianhao Miao, Yanjiao Chen +3
Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable…
Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
Xinfeng Li, Shengyuan Pang, Jialin Wu +5
Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderati…
Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
Jialin Wu, Kaikai Pan, Yanjiao Chen +3
Transformer models have excelled in natural language tasks, prompting the vision community to explore their implementation in computer vision problems. However, these models are st…
SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
Xinfeng Li, Yuchen Yang, Jiangyi Deng +4
Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-…