Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however, are effective only for specific pre-defined downstream tasks. In reality, these PTLMs can be adapted to many other unrelated downstream tasks. Such adaptation may lead to unforeseen consequences in downstream model outputs, consequently raising user suspicion and compromising attack stealthiness. We refer to this phenomenon as backdoor complications. In this paper, we undertake the first comprehensive quantification of backdoor complications. Through extensive experiments using 4 prominent PTLMs and 16 text classification benchmark datasets, we demonstrate the widespread presence of backdoor complications in downstream models fine-tuned from backdoored PTLMs. The output distribution of triggered samples significantly deviates from that of clean samples. Consequently, we propose a backdoor complication reduction method leveraging multi-task learning to mitigate complications without prior knowledge of downstream tasks. The experimental results demonstrate that our proposed method can effectively reduce complications while maintaining the efficacy and consistency of backdoor attacks. Our code is available at https://github.com/zhangrui4041/Backdoor_Complications.

Large language models (LLMs) have facilitated the generation of high-quality, cost-effective synthetic data for developing downstream models and conducting statistical analyses in various domains. However, the increased reliance on synthetic data may pose potential negative impacts. Numerous studies have demonstrated that LLM-generated synthetic data can perpetuate and even amplify societal biases and stereotypes, and produce erroneous outputs known as "hallucinations" that deviate from factual knowledge. In this paper, we aim to audit artifacts, such as classifiers, generators, or statistical plots, to identify those trained on or derived from synthetic data and raise user awareness, thereby reducing unexpected consequences and risks in downstream applications. To this end, we take the first step to introduce synthetic artifact auditing to assess whether a given artifact is derived from LLM-generated synthetic data. We then propose an auditing framework with three methods including metric-based auditing, tuning-based auditing, and classification-based auditing. These methods operate without requiring the artifact owner to disclose proprietary training details. We evaluate our auditing framework on three text classification tasks, two text summarization tasks, and two data visualization tasks across three training scenarios. Our evaluation demonstrates the effectiveness of all proposed auditing methods across all these tasks. For instance, blackbox metric-based auditing can achieve an average accuracy of 0.868 +/- 0.071 for auditing classifiers and 0.880 +/- 0.052 for auditing generators using only 200 random queries across three scenarios. We hope our research will enhance model transparency and regulatory compliance, ensuring the ethical and responsible use of synthetic data.(1)

The tremendous commercial potential of large language models (LLMs) has heightened concerns about their unauthorized use. Third parties can customize LLMs through fine-tuning and offer only black-box API access, effectively concealing unauthorized usage and complicating external auditing processes. This practice not only exacerbates unfair competition, but also violates licensing agreements. In response, identifying the origin of black-box LLMs is an intrinsic solution to this issue. In this paper, we first reveal the limitations of state-of-the-art passive and proactive identification methods with experiments on 30 LLMs and two real-world black-box APIs. Then, we propose the proactive technique, PlugAE, which optimizes adversarial token embeddings in a continuous space and proactively plugs them into the LLM for tracing and identification. The experiments show that PlugAE can achieve substantial improvement in identifying fine-tuned derivatives. We further advocate for legal frameworks and regulations to better address the challenges posed by the unauthorized use of LLMs.

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.

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may covertly introduce vulnerabilities for downstream tasks. In this paper, we explore the vulnerability of LLMs through the lens of backdoor attacks. Different from existing backdoor attacks against LLMs, ours scatters multiple trigger keys in different prompt components. Such a Composite Backdoor Attack (CBA) is shown to be stealthier than implanting the same multiple trigger keys in only a single component. CBA ensures that the backdoor is activated only when all trigger keys appear. Our experiments demonstrate that CBA is effective in both natural language processing (NLP) and multimodal tasks. For instance, with $3\%$ poisoning samples against the LLaMA-7B model on the Emotion dataset, our attack achieves a $100\%$ Attack Success Rate (ASR) with a False Triggered Rate (FTR) below $2.06\%$ and negligible model accuracy degradation. Our work highlights the necessity of increased security research on the trustworthiness of foundation LLMs.

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only learns an input perturbation, namely prompt, to be added to the downstream task data for predictions. Given the fast development of prompt learning, a well-generalized prompt inevitably becomes a valuable asset as significant effort and proprietary data are used to create it. This naturally raises the question of whether a prompt may leak the proprietary information of its training data. In this paper, we perform the first comprehensive privacy assessment of prompts learned by visual prompt learning through the lens of property inference and membership inference attacks. Our empirical evaluation shows that the prompts are vulnerable to both attacks. We also demonstrate that the adversary can mount a successful property inference attack with limited cost. Moreover, we show that membership inference attacks against prompts can be successful with relaxed adversarial assumptions. We further make some initial investigations on the defenses and observe that our method can mitigate the membership inference attacks with a decent utility-defense trade-off but fails to defend against property inference attacks. We hope our results can shed light on the privacy risks of the popular prompt learning paradigm. To facilitate the research in this direction, we will share our code and models with the community.

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.

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 6 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 two defense strategies and demonstrate their effectiveness in reducing such attacks. Our findings highlight the vulnerability and the potential risks of LLM customization such as GPTs.

Fine-tuning large pre-trained computer vision models is infeasible for resource-limited users. Visual prompt learning (VPL) has thus emerged to provide an efficient and flexible alternative to model fine-tuning through Visual Prompt as a Service (VPPTaaS). Specifically, the VPPTaaS provider optimizes a visual prompt given downstream data, and downstream users can use this prompt together with the large pre-trained model for prediction. However, this new learning paradigm may also pose security risks when the VPPTaaS provider instead provides a malicious visual prompt. In this paper, we take the first step to explore such risks through the lens of backdoor attacks. Specifically, we propose BadVisualPrompt, a simple yet effective backdoor attack against VPL. For example, poisoning $5\%$ CIFAR10 training data leads to above $99\%$ attack success rates with only negligible model accuracy drop by $1.5\%$. In particular, we identify and then address a new technical challenge related to interactions between the backdoor trigger and visual prompt, which does not exist in conventional, model-level backdoors. Moreover, we provide in-depth analyses of seven backdoor defenses from model, prompt, and input levels. Overall, all these defenses are either ineffective or impractical to mitigate our BadVisualPrompt, implying the critical vulnerability of VPL.

The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of the problem, research focuses on developing solutions to detect toxic content, usually leveraging machine learning (ML) models trained on human-annotated datasets. While these efforts are important, these models usually do not generalize well and they can not cope with new trends (e.g., the emergence of new toxic terms). Currently, we are witnessing a shift in the approach to tackling societal issues online, particularly leveraging large language models (LLMs) like GPT-3 or T5 that are trained on vast corpora and have strong generalizability. In this work, we investigate how we can use LLMs and prompt learning to tackle the problem of toxic content, particularly focusing on three tasks; 1) Toxicity Classification, 2) Toxic Span Detection, and 3) Detoxification. We perform an extensive evaluation over five model architectures and eight datasets demonstrating that LLMs with prompt learning can achieve similar or even better performance compared to models trained on these specific tasks. We find that prompt learning achieves around 10% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0.643 vs. 0.640 in terms of F 1 -score). Finally, for the detoxification task, we find that prompt learning can successfully reduce the average toxicity score (from 0.775 to 0.213) while preserving semantic meaning. 1

The misuse of large language models (LLMs) has drawn significant attention from the general public and LLM vendors. One particular type of adversarial prompt, known as jailbreak prompt, has emerged as the main attack vector to bypass the safeguards and elicit harmful content from LLMs. In this paper, employing our new framework JailbreakHub, we conduct a comprehensive analysis of 1,405 jailbreak prompts spanning from December 2022 to December 2023. We identify 131 jailbreak communities and discover unique characteristics of jailbreak prompts and their major attack strategies, such as prompt injection and privilege escalation. We also observe that jailbreak prompts increasingly shift from online Web communities to prompt-aggregation websites and 28 user accounts have consistently optimized jailbreak prompts over 100 days. To assess the potential harm caused by jailbreak prompts, we create a question set comprising 107,250 samples across 13 forbidden scenarios. Leveraging this dataset, our experiments on six popular LLMs show that their safeguards cannot adequately defend jailbreak prompts in all scenarios. Particularly, we identify five highly effective jailbreak prompts that achieve 0.95 attack success rates on ChatGPT (GPT-3.5) and GPT-4, and the earliest one has persisted online for over 240 days. We hope that our study can facilitate the research community and LLM vendors in promoting safer and regulated LLMs.

Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP. The emerging large language models (LLMs), such as ChatGPT, can potentially further accentuate this threat. Previous works have discovered that ChatGPT can generate toxic responses using carefully crafted inputs. However, limited research has been done to systematically examine when ChatGPT generates toxic responses. In this paper, we comprehensively evaluate the toxicity in ChatGPT by utilizing instruction-tuning datasets that closely align with real-world scenarios. Our results show that ChatGPT's toxicity varies based on different properties and settings of the prompts, including tasks, domains, length, and languages. Notably, prompts in creative writing tasks can be 2x more likely than others to elicit toxic responses. Prompting in German and Portuguese can also double the response toxicity. Additionally, we discover that certain deliberately toxic prompts, designed in earlier studies, no longer yield harmful responses. We hope our discoveries can guide model developers to better regulate these AI systems and the users to avoid undesirable outputs.

Graph generative models become increasingly effective for data distribution approximation and data augmentation. While they have aroused public concerns about their malicious misuses or misinformation broadcasts, just as what Deepfake visual and auditory media has been delivering to society. Hence it is essential to regulate the prevalence of generated graphs. To tackle this problem, we pioneer the formulation of the generated graph detection problem to distinguish generated graphs from real ones. We propose the first framework to systematically investigate a set of sophisticated models and their performance in four classification scenarios. Each scenario switches between seen and unseen datasets/generators during testing to get closer to real-world settings and progressively challenge the classifiers. Extensive experiments evidence that all the models are qualified for generated graph detection, with specific models having advantages in specific scenarios. Resulting from the validated generality and oblivion of the classifiers to unseen datasets/generators, we draw a safe conclusion that our solution can sustain for a decent while to curb generated graph misuses.

Many real-world data are graphs, such as social networks and protein structures. To fully utilize the information contained in graph data, graph neural networks (GNNs) have been introduced. Previous studies have shown that machine learning models are vulnerable to privacy attacks. However, most of the current efforts concentrate on ML models trained on images and texts. On the other hand, privacy risks stemming from GNNs remain largely unstudied. In this paper, we fill the gap by performing the first comprehensive analysis of node-level membership inference attacks against GNNs. We systematically define the threat models and propose eight node-level membership inference attacks based on an adversary's background knowledge. Our evaluation on four GNN structures and four benchmark datasets shows that GNNs are vulnerable to node-level membership inference even when the adversary has minimal background knowledge. Besides, we show that node degree, graph density, and feature similarity have major impacts on the attack's success. We further investigate three defense mechanisms and show that differential privacy (DP) can better protect the membership privacy while preserving the model's utility.

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking and reconstructing random patches of the input image. However, the associated security and privacy risks of this novel generative method are unexplored. In this paper, we perform the first security risk quantification of MIM through the lens of backdoor attacks. Different from previous work, we are the first to systematically threat modeling on SSL in every phase of the model supply chain, i.e., pre-training, release, and downstream phases. Our evaluation shows that models built with MIM are vulnerable to existing backdoor attacks in release and downstream phases and are compromised by our proposed method in pre-training phase. For instance, on CIFAR10, the attack success rate can reach 99.62%, 96.48%, and 98.89% in the downstream phase, release phase, and pre-training phase, respectively. We also take the first step to investigate the success factors of backdoor attacks in the pre-training phase and find the trigger number and trigger pattern play key roles in the success of backdoor attacks while trigger location has only tiny effects. In the end, our empirical study of the defense mechanisms across three detection-level on model supply chain phases indicates that different defenses are suitable for backdoor attacks in different phases. However, backdoor attacks in the release phase cannot be detected by all three detection-level methods, calling for more effective defenses in future research.

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs, which can generalize to unseen data, become mainstream in this direction. Machine learning models have shown great potential in various tasks and have been deployed in many real-world scenarios. To train a good model, a large amount of data as well as computational resources are needed, leading to valuable intellectual property. Previous research has shown that ML models are prone to model stealing attacks, which aim to steal the functionality of the target models. However, most of them focus on the models trained with images and texts. On the other hand, little attention has been paid to models trained with graph data, i.e., GNNs. In this paper, we fill the gap by proposing the first model stealing attacks against inductive GNNs. We systematically define the threat model and propose six attacks based on the adversary's background knowledge and the responses of the target models. Our evaluation on six benchmark datasets shows that the proposed model stealing attacks against GNNs achieve promising performance.

Graph is an important data representation ubiquitously existing in the real world. However, analyzing the graph data is computationally difficult due to its non-Euclidean nature. Graph embedding is a powerful tool to solve the graph analytics problem by transforming the graph data into low-dimensional vectors. These vectors could also be shared with third parties to gain additional insights of what is behind the data. While sharing graph embedding is intriguing, the associated privacy risks are unexplored. In this paper, we systematically investigate the information leakage of the graph embedding by mounting three inference attacks. First, we can successfully infer basic graph properties, such as the number of nodes, the number of edges, and graph density, of the target graph with up to 0.89 accuracy. Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph. For instance, we achieve 0.98 attack AUC on the DD dataset. Third, we propose a novel graph reconstruction attack that can reconstruct a graph that has similar graph structural statistics to the target graph. We further propose an effective defense mechanism based on graph embedding perturbation to mitigate the inference attacks without noticeable performance degradation for graph classification tasks. Our code is available at https://github.com/Zhangzhk0819/GNN-Embedding-Leaks.

Modern defenses against cyberattacks increasingly rely on proactive approaches, e.g., to predict the adversary's next actions based on past events. Building accurate prediction models requires knowledge from many organizations; alas, this entails disclosing sensitive information, such as network structures, security postures, and policies, which might often be undesirable or outright impossible.

As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction. In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples. To this end, we demonstrate a set of data poisoning attacks to amplify the membership exposure of the targeted class. We first propose a generic dirty-label attack for supervised classification algorithms. We then propose an optimization-based clean-label attack in the transfer learning scenario, whereby the poisoning samples are correctly labeled and look "natural" to evade human moderation. We extensively evaluate our attacks on computer vision benchmarks. Our results show that the proposed attacks can substantially increase the membership inference precision with minimum overall test-time model performance degradation. To mitigate the potential negative impacts of our attacks, we also investigate feasible countermeasures.

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs, which can generalize to unseen data, become mainstream in this direction. Machine learning models have shown great potential in various tasks and have been deployed in many real-world scenarios. To train a good model, a large amount of data as well as computational resources are needed, leading to valuable intellectual property. Previous research has shown that ML models are prone to model stealing attacks, which aim to steal the functionality of the target models. However, most of them focus on the models trained with images and texts. On the other hand, little attention has been paid to models trained with graph data, i.e., GNNs. In this paper, we fill the gap by proposing the first model stealing attacks against inductive GNNs. We systematically define the threat model and propose six attacks based on the adversary's background knowledge and the responses of the target models. Our evaluation on six benchmark datasets shows that the proposed model stealing attacks against GNNs achieve promising performance.