How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities

• URL: http://arxiv.org/abs/2311.09447v2
• Date: Tue, 2 Apr 2024 15:21:55 GMT
• Title: How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
• Authors: Lingbo Mo, Boshi Wang, Muhao Chen, Huan Sun,
• Abstract summary: We conduct an adversarial assessment of open-source Large Language Models (LLMs) on trustworthiness. We propose advCoU, an extended Chain of Utterances-based (CoU) prompting strategy by incorporating carefully crafted malicious demonstrations for trustworthiness attack. Our experiments encompass recent and representative series of open-source LLMs, including Vicuna, MPT, Falcon, Mistral, and Llama 2.
• Score: 37.14654106278984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid progress in open-source Large Language Models (LLMs) is significantly driving AI development forward. However, there is still a limited understanding of their trustworthiness. Deploying these models at scale without sufficient trustworthiness can pose significant risks, highlighting the need to uncover these issues promptly. In this work, we conduct an adversarial assessment of open-source LLMs on trustworthiness, scrutinizing them across eight different aspects including toxicity, stereotypes, ethics, hallucination, fairness, sycophancy, privacy, and robustness against adversarial demonstrations. We propose advCoU, an extended Chain of Utterances-based (CoU) prompting strategy by incorporating carefully crafted malicious demonstrations for trustworthiness attack. Our extensive experiments encompass recent and representative series of open-source LLMs, including Vicuna, MPT, Falcon, Mistral, and Llama 2. The empirical outcomes underscore the efficacy of our attack strategy across diverse aspects. More interestingly, our result analysis reveals that models with superior performance in general NLP tasks do not always have greater trustworthiness; in fact, larger models can be more vulnerable to attacks. Additionally, models that have undergone instruction tuning, focusing on instruction following, tend to be more susceptible, although fine-tuning LLMs for safety alignment proves effective in mitigating adversarial trustworthiness attacks.

Related papers

• Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks [23.782566331783134]
  We focus on 10 cutting-edge jailbreak strategies across three categories, 1525 questions from 61 specific harmful categories, and 13 popular LLMs. We adopt multi-dimensional metrics such as Attack Success Rate (ASR), Toxicity Score, Fluency, Token Length, and Grammatical Errors to thoroughly assess the LLMs' outputs under jailbreak. We explore the relationships among the models, attack strategies, and types of harmful content, as well as the correlations between the evaluation metrics, which proves the validity of our multifaceted evaluation framework.
  arXiv  Detail & Related papers  (2024-08-18T01:58:03Z)
• Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study [51.19622266249408]
  MultiTrust is the first comprehensive and unified benchmark on the trustworthiness of MLLMs. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks.
  arXiv  Detail & Related papers  (2024-06-11T08:38:13Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes [0.0]
  Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. These models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection, and privacy leakage attacks. This study investigates the impact of these modifications on LLM safety, a critical consideration for building reliable and secure AI systems.
  arXiv  Detail & Related papers  (2024-04-05T20:31:45Z)
• TrustLLM: Trustworthiness in Large Language Models [446.5640421311468]
  This paper introduces TrustLLM, a comprehensive study of trustworthiness in large language models (LLMs) We first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics.
  arXiv  Detail & Related papers  (2024-01-10T22:07:21Z)
• Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
  We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks. We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
  arXiv  Detail & Related papers  (2023-06-22T22:13:03Z)
• On Evaluating Adversarial Robustness of Large Vision-Language Models [64.66104342002882]
  We evaluate the robustness of large vision-language models (VLMs) in the most realistic and high-risk setting. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP. Black-box queries on these VLMs can further improve the effectiveness of targeted evasion.
  arXiv  Detail & Related papers  (2023-05-26T13:49:44Z)

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.