9 papers
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
Zedian Shao, Charles Fleming, Teodora Baluta
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that de…
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
Zedian Shao, Hongbin Liu, Yuepeng Hu +1
Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and…
Watermark Robustness and Radioactivity May Be at Odds in Federated Learning
Leixu Huang, Zedian Shao, Teodora Baluta
Federated learning (FL) enables fine-tuning large language models (LLMs) across distributed data sources. As these sources increasingly include LLM-generated text, provenance track…
PromptLocate: Localizing Prompt Injection Attacks
Yuqi Jia, Yupei Liu, Zedian Shao +2
Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected pro…
WebInject: Prompt Injection Attack to Web Agents
Xilong Wang, John Bloch, Zedian Shao +3
Multi-modal large language model (MLLM)-based web agents interact with webpage environments by generating actions based on screenshots of the webpages. In this work, we propose Web…
Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
Zedian Shao, Hongbin Liu, Jaden Mu +1
Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-ch…