The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness of third-party custom versions of LLMs remains an essential concern. In this paper, we propose the first instruction backdoor attacks against applications integrated with untrusted customized LLMs (e.g., GPTs). Specifically, these attacks embed the backdoor into the custom version of LLMs by designing prompts with backdoor instructions, outputting the attacker's desired result when inputs contain the pre-defined triggers. Our attack includes 3 levels of attacks: word-level, syntax-level, and semantic-level, which adopt different types of triggers with progressive stealthiness. We stress that our attacks do not require fine-tuning or any modification to the backend LLMs, adhering strictly to GPTs development guidelines. We conduct extensive experiments on 4 prominent LLMs and 5 benchmark text classification datasets. The results show that our instruction backdoor attacks achieve the desired attack performance without compromising utility. Additionally, we propose an instruction-ignoring defense mechanism and demonstrate its partial effectiveness in mitigating such attacks. Our findings highlight the vulnerability and the potential risks of LLM customization such as GPTs.
Misuse of the Large Language Models (LLMs) has raised widespread concern. To address this issue, safeguards have been taken to ensure that LLMs align with social ethics. However, recent findings have revealed an unsettling vulnerability bypassing the safeguards of LLMs, known as jailbreak attacks. By applying techniques, such as employing role-playing scenarios, adversarial examples, or subtle subversion of safety objectives as a prompt, LLMs can produce an inappropriate or even harmful response. While researchers have studied several categories of jailbreak attacks, they have done so in isolation. To fill this gap, we present the first large-scale measurement of various jailbreak attack methods. We concentrate on 13 cutting-edge jailbreak methods from four categories, 160 questions from 16 violation categories, and six popular LLMs. Our extensive experimental results demonstrate that the optimized jailbreak prompts consistently achieve the highest attack success rates, as well as exhibit robustness across different LLMs. Some jailbreak prompt datasets, available from the Internet, can also achieve high attack success rates on many LLMs, such as ChatGLM3, GPT-3.5, and PaLM2. Despite the claims from many organizations regarding the coverage of violation categories in their policies, the attack success rates from these categories remain high, indicating the challenges of effectively aligning LLM policies and the ability to counter jailbreak attacks. We also discuss the trade-off between the attack performance and efficiency, as well as show that the transferability of the jailbreak prompts is still viable, becoming an option for black-box models. Overall, our research highlights the necessity of evaluating different jailbreak methods. We hope our study can provide insights for future research on jailbreak attacks and serve as a benchmark tool for evaluating them for practitioners.
In recent times, significant advancements have been made in the field of large language models (LLMs), represented by GPT series models. To optimize task execution, users often engage in multi-round conversations with GPT models hosted in cloud environments. These multi-round conversations, potentially replete with private information, require transmission and storage within the cloud. However, this operational paradigm introduces additional attack surfaces. In this paper, we first introduce a specific Conversation Reconstruction Attack targeting GPT models. Our introduced Conversation Reconstruction Attack is composed of two steps: hijacking a session and reconstructing the conversations. Subsequently, we offer an exhaustive evaluation of the privacy risks inherent in conversations when GPT models are subjected to the proposed attack. However, GPT-4 demonstrates certain robustness to the proposed attacks. We then introduce two advanced attacks aimed at better reconstructing previous conversations, specifically the UNR attack and the PBU attack. Our experimental findings indicate that the PBU attack yields substantial performance across all models, achieving semantic similarity scores exceeding 0.60, while the UNR attack is effective solely on GPT-3.5. Our results reveal the concern about privacy risks associated with conversations involving GPT models and aim to draw the community's attention to prevent the potential misuse of these models' remarkable capabilities. We will responsibly disclose our findings to the suppliers of related large language models.
Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.
Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data-often scraped from the internet. This data can still be sensitive and empirical evidence suggests that SSL encoders memorize private information of their training data and can disclose them at inference time. Since existing theoretical definitions of memorization from supervised learning rely on labels, they do not transfer to SSL. To address this gap, we propose SSLMem, a framework for defining memorization within SSL. Our definition compares the difference in alignment of representations for data points and their augmented views returned by both encoders that were trained on these data points and encoders that were not. Through comprehensive empirical analysis on diverse encoder architectures and datasets we highlight that even though SSL relies on large datasets and strong augmentations-both known in supervised learning as regularization techniques that reduce overfitting-still significant fractions of training data points experience high memorization. Through our empirical results, we show that this memorization is essential for encoders to achieve higher generalization performance on different downstream tasks.
To prevent the mischievous use of synthetic (fake) point clouds produced by generative models, we pioneer the study of detecting point cloud authenticity and attributing them to their sources. We propose an attribution framework, FAKEPCD, to attribute (fake) point clouds to their respective generative models (or real-world collections). The main idea of FAKEPCD is to train an attribution model that learns the point cloud features from different sources and further differentiates these sources using an attribution signal. Depending on the characteristics of the training point clouds, namely, sources and shapes, we formulate four attribution scenarios: close-world, open-world, single-shape, and multiple-shape, and evaluate FAKEPCD's performance in each scenario. Extensive experimental results demonstrate the effectiveness of FAKEPCD on source attribution across different scenarios. Take the open-world attribution as an example, FAKEPCD attributes point clouds to known sources with an accuracy of 0.82-0.98 and to unknown sources with an accuracy of 0.73-1.00. Additionally, we introduce an approach to visualize unique patterns (fingerprints) in point clouds associated with each source. This explains how FAKEPCD recognizes point clouds from various sources by focusing on distinct areas within them. Overall, we hope our study establishes a baseline for the source attribution of (fake) point clouds.
Generative models have demonstrated revolutionary success in various visual creation tasks, but in the meantime, they have been exposed to the threat of leaking private information of their training data. Several membership inference attacks (MIAs) have been proposed to exhibit the privacy vulnerability of generative models by classifying a query image as a training dataset member or nonmember. However, these attacks suffer from major limitations, such as requiring shadow models and white-box access, and either ignoring or only focusing on the unique property of diffusion models, which block their generalization to multiple generative models. In contrast, we propose the first generalized membership inference attack against a variety of generative models such as generative adversarial networks, [variational] autoencoders, implicit functions, and the emerging diffusion models. We leverage only generated distributions from target generators and auxiliary non-member datasets, therefore regarding target generators as black boxes and agnostic to their architectures or application scenarios. Experiments validate that all the generative models are vulnerable to our attack. For instance, our work achieves attack AUC $>0.99$ against DDPM, DDIM, and FastDPM trained on CIFAR-10 and CelebA. And the attack against VQGAN, LDM (for the text-conditional generation), and LIIF achieves AUC $>0.90.$ As a result, we appeal to our community to be aware of such privacy leakage risks when designing and publishing generative models.
While advanced machine learning (ML) models are deployed in numerous real-world applications, previous works demonstrate these models have security and privacy vulnerabilities. Various empirical research has been done in this field. However, most of the experiments are performed on target ML models trained by the security researchers themselves. Due to the high computational resource requirement for training advanced models with complex architectures, researchers generally choose to train a few target models using relatively simple architectures on typical experiment datasets. We argue that to understand ML models' vulnerabilities comprehensively, experiments should be performed on a large set of models trained with various purposes (not just the purpose of evaluating ML attacks and defenses). To this end, we propose using publicly available models with weights from the Internet (public models) for evaluating attacks and defenses on ML models. We establish a database, namely SecurityNet, containing 910 annotated image classification models. We then analyze the effectiveness of several representative attacks/defenses, including model stealing attacks, membership inference attacks, and backdoor detection on these public models. Our evaluation empirically shows the performance of these attacks/defenses can vary significantly on public models compared to self-trained models. We share SecurityNet with the research community. and advocate researchers to perform experiments on public models to better demonstrate their proposed methods' effectiveness in the future.
Transferable adversarial examples raise critical security concerns in real-world, black-box attack scenarios. However, in this work, we identify two main problems in common evaluation practices: (1) For attack transferability, lack of systematic, one-to-one attack comparison and fair hyperparameter settings. (2) For attack stealthiness, simply no comparisons. To address these problems, we establish new evaluation guidelines by (1) proposing a novel attack categorization strategy and conducting systematic and fair intra-category analyses on transferability, and (2) considering diverse imperceptibility metrics and finer-grained stealthiness characteristics from the perspective of attack traceback. To this end, we provide the first large-scale evaluation of transferable adversarial examples on ImageNet, involving 23 representative attacks against 9 representative defenses. Our evaluation leads to a number of new insights, including consensus-challenging ones: (1) Under a fair attack hyperparameter setting, one early attack method, DI, actually outperforms all the follow-up methods. (2) A state-of-the-art defense, DiffPure, actually gives a false sense of (white-box) security since it is indeed largely bypassed by our (black-box) transferable attacks. (3) Even when all attacks are bounded by the same $L_p$ norm, they lead to dramatically different stealthiness performance, which negatively correlates with their transferability performance. Overall, our work demonstrates that existing problematic evaluations have indeed caused misleading conclusions and missing points, and as a result, hindered the assessment of the actual progress in this field.