Tian Dong (Shanghai Jiao Tong University), Minhui Xue (CSIRO's Data61), Guoxing Chen (Shanghai Jiao Tong University), Rayne Holland (CSIRO's Data61), Yan Meng (Shanghai Jiao Tong University), Shaofeng Li (Southeast University), Zhen Liu (Shanghai Jiao Tong University), Haojin Zhu (Shanghai Jiao Tong University)

Open-source Large Language Models (LLMs) have recently gained popularity because of their comparable performance to proprietary LLMs. To efficiently fulfill domain-specialized tasks, open-source LLMs can be refined, without expensive accelerators, using low-rank adapters. However, it is still unknown whether low-rank adapters can be exploited to control LLMs. To address this gap, we demonstrate that an infected adapter can induce, on specific triggers, an LLM to output content defined by an adversary and to even maliciously use tools. To train a Trojan adapter, we propose two novel attacks, POLISHED and FUSION, that improve over prior approaches. POLISHED uses a superior LLM to align naïvely poisoned data based on our insight that it can better inject poisoning knowledge during training. In contrast, FUSION leverages a novel over-poisoning procedure to transform a benign adapter into a malicious one by magnifying the attention between trigger and target in model weights. In our experiments, we first conduct two case studies to demonstrate that a compromised LLM agent can use malware to control the system (e.g., a LLM-driven robot) or to launch a spear-phishing attack. Then, in terms of targeted misinformation, we show that our attacks provide higher attack effectiveness than the existing baseline and, for the purpose of attracting downloads, preserve or improve the adapter’s utility. Finally, we designed and evaluated three potential defenses. However, none proved entirely effective in safeguarding against our attacks, highlighting the need for more robust defenses supporting a secure LLM supply chain.

View More Papers

Panel on “Security and Privacy Issues in New 5G...

Moderator: Arupjyoti (Arup) Bhuyan, Ph.D. Director, Wireless Security Institute, Idaho National Laboratory Panelists: Ted K. Woodward, Ph.D. Technical Director for FutureG, OUSD (R&E) Phillip Porras, Program Director, Internet Security Research, SRI Donald McBride, Senior Security Researcher, Bell Laboratories, Nokia

Read More

Evaluating Machine Learning-Based IoT Device Identification Models for Security...

Eman Maali (Imperial College London), Omar Alrawi (Georgia Institute of Technology), Julie McCann (Imperial College London)

Read More

BumbleBee: Secure Two-party Inference Framework for Large Transformers

Wen-jie Lu (Ant Group), Zhicong Huang (Ant Group), Zhen Gu (Alibaba Group), Jingyu Li (Ant Group & Zhejiang University), Jian Liu (Zhejiang University), Cheng Hong (Ant Group), Kui Ren (Zhejiang University), Tao Wei (Ant Group), WenGuang Chen (Ant Group)

Read More

GadgetMeter: Quantitatively and Accurately Gauging the Exploitability of Speculative...

Qi Ling (Purdue University), Yujun Liang (Tsinghua University), Yi Ren (Tsinghua University), Baris Kasikci (University of Washington and Google), Shuwen Deng (Tsinghua University)

Read More