The Philosopher's Stone: Trojaning Plugins of Large Language Models

• URL: http://arxiv.org/abs/2312.00374v3
• Date: Wed, 11 Sep 2024 12:48:42 GMT
• Title: The Philosopher's Stone: Trojaning Plugins of Large Language Models
• Authors: Tian Dong, Minhui Xue, Guoxing Chen, Rayne Holland, Yan Meng, Shaofeng Li, Zhen Liu, Haojin Zhu,
• Abstract summary: 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. It is still unknown whether low-rank adapters can be exploited to control LLMs.
• Score: 22.67696768099352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 na\"ively 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.

Related papers

• Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks [88.84977282952602]
  A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs) In this paper, we analyze security and privacy vulnerabilities that are unique to LLM agents. We conduct a series of illustrative attacks on popular open-source and commercial agents, demonstrating the immediate practical implications of their vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-12T17:19:36Z)
• Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context [49.13497493053742]
  This research explores converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs.
  arXiv  Detail & Related papers  (2024-07-19T19:47:26Z)
• MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants [14.947665219536708]
  We introduce the Malicious Programming Prompt (MaPP) attack, in which an attacker adds a small amount of text to a prompt for a programming task. We show that our prompt strategy can cause an LLM to add vulnerabilities while continuing to write otherwise correct code.
  arXiv  Detail & Related papers  (2024-07-12T22:30:35Z)
• ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings [58.82536530615557]
  We propose an Adversarial Suffix Embedding Translation Framework (ASETF) to transform continuous adversarial suffix embeddings into coherent and understandable text. Our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate to existing techniques.
  arXiv  Detail & Related papers  (2024-02-25T06:46:27Z)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)
• TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models [29.66515518909497]
  TrojLLM is an automatic and black-box framework to generate universal and stealthy triggers. It supports embedding Trojans within discrete prompts, enhancing the overall effectiveness and precision of the triggers' attacks. Our experiments and results demonstrate TrojLLM's capacity to effectively insert Trojans into text prompts in real-world black-box LLM APIs.
  arXiv  Detail & Related papers  (2023-06-12T01:22:39Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)
• Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks [67.86285142381644]
  Recent advances in instruction-following large language models amplify the dual-use risks for malicious purposes. Dual-use is difficult to prevent as instruction-following capabilities now enable standard attacks from computer security. We show that instruction-following LLMs can produce targeted malicious content, including hate speech and scams.
  arXiv  Detail & Related papers  (2023-02-11T15:57:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.