Deep learning models have been incorporated into high-stakes sectors, including healthcare diagnosis, loan approvals, and candidate recruitment, among others. Consequently, any bias or unfairness in these models can harm those who depend on such models. In response, many algorithms have emerged to ensure fairness in deep learning. However, while the potential for harm is substantial, the resilience of these fair deep learning models against malicious attacks has never been thoroughly explored, especially in the context of emerging Trojan attacks. Moving beyond prior research, we aim to fill this void by introducing \textit{TrojFair}, a Trojan fairness attack. Unlike existing attacks, TrojFair is model-agnostic and crafts a Trojaned model that functions accurately and equitably for clean inputs. However, it displays discriminatory behaviors \text{-} producing both incorrect and unfair results \text{-} for specific groups with tainted inputs containing a trigger. TrojFair is a stealthy Fairness attack that is resilient to existing model fairness audition detectors since the model for clean inputs is fair. TrojFair achieves a target group attack success rate exceeding $88.77\%$, with an average accuracy loss less than $0.44\%$. It also maintains a high discriminative score between the target and non-target groups across various datasets and models.
Prompt tuning is one of the most effective solutions to adapting a fixed pre-trained language model (PLM) for various downstream tasks, especially with only a few input samples. However, the security issues, e.g., Trojan attacks, of prompt tuning on a few data samples are not well-studied. Transferring established data poisoning attacks directly to few-shot prompt tuning presents multiple challenges. One significant issue is the \textit{poisoned imbalance issue}, where non-target class samples are added to the target class, resulting in a greater number of target-class samples compared to non-target class. While this issue is not critical in regular tuning, it significantly hampers the few-shot prompt tuning, making it difficult to simultaneously achieve a high attack success rate (ASR) and maintain clean data accuracy (CDA). Additionally, few-shot prompting is prone to overfitting in terms of both ASR and CDA. In this paper, we introduce \textit{TrojFSP}, a method designed to address the challenges. To solve the poisoned imbalance issue, we develop a \textit{Target-Class Shrink (TC-Shrink)} technique, which aims to equalize the number of poisoning samples. To combat overfitting, we employ a \textit{Selective Token Poisoning} technique to boost attack performance. Furthermore, we introduce a \textit{Trojan-Trigger Attention} objective function to amplify the attention of the poisoned trojan prompt on triggers. Experiments show that our TrojFSP achieves an ASR of over 99\% while maintaining negligible decreases in CDA across various PLMs and datasets.
Prompt learning has been proven to be highly effective in improving pre-trained language model (PLM) adaptability, surpassing conventional fine-tuning paradigms, and showing exceptional promise in an ever-growing landscape of applications and APIs tailored for few-shot learning scenarios. Despite the growing prominence of prompt learning-based APIs, their security concerns remain underexplored. In this paper, we undertake a pioneering study on the Trojan susceptibility of prompt-learning PLM APIs. We identified several key challenges, including discrete-prompt, few-shot, and black-box settings, which limit the applicability of existing backdoor attacks. To address these challenges, we propose TrojPrompt, an automatic and black-box framework to effectively generate universal and stealthy triggers and insert Trojans into hard prompts. Specifically, we propose a universal API-driven trigger discovery algorithm for generating universal triggers for various inputs by querying victim PLM APIs using few-shot data samples. Furthermore, we introduce a novel progressive trojan poisoning algorithm designed to generate poisoned prompts that retain efficacy and transferability across a diverse range of models. Our experiments and results demonstrate TrojPrompt's capacity to effectively insert Trojans into text prompts in real-world black-box PLM APIs, while maintaining exceptional performance on clean test sets and significantly outperforming baseline models. Our work sheds light on the potential security risks in current models and offers a potential defensive approach.
Self-supervised learning (SSL) is a commonly used approach to learning and encoding data representations. By using a pre-trained SSL image encoder and training a downstream classifier on top of it, impressive performance can be achieved on various tasks with very little labeled data. The increasing usage of SSL has led to an uptick in security research related to SSL encoders and the development of various Trojan attacks. The danger posed by Trojan attacks inserted in SSL encoders lies in their ability to operate covertly and spread widely among various users and devices. The presence of backdoor behavior in Trojaned encoders can inadvertently be inherited by downstream classifiers, making it even more difficult to detect and mitigate the threat. Although current Trojan detection methods in supervised learning can potentially safeguard SSL downstream classifiers, identifying and addressing triggers in the SSL encoder before its widespread dissemination is a challenging task. This is because downstream tasks are not always known, dataset labels are not available, and even the original training dataset is not accessible during the SSL encoder Trojan detection. This paper presents an innovative technique called SSL-Cleanse that is designed to detect and mitigate backdoor attacks in SSL encoders. We evaluated SSL-Cleanse on various datasets using 300 models, achieving an average detection success rate of 83.7% on ImageNet-100. After mitigating backdoors, on average, backdoored encoders achieve 0.24% attack success rate without great accuracy loss, proving the effectiveness of SSL-Cleanse.
In Natural Language Processing (NLP), intelligent neuron models can be susceptible to textual Trojan attacks. Such attacks occur when Trojan models behave normally for standard inputs but generate malicious output for inputs that contain a specific trigger. Syntactic-structure triggers, which are invisible, are becoming more popular for Trojan attacks because they are difficult to detect and defend against. However, these types of attacks require a large corpus of training data to generate poisoned samples with the necessary syntactic structures for Trojan insertion. Obtaining such data can be difficult for attackers, and the process of generating syntactic poisoned triggers and inserting Trojans can be time-consuming. This paper proposes a solution called TrojText, which aims to determine whether invisible textual Trojan attacks can be performed more efficiently and cost-effectively without training data. The proposed approach, called the Representation-Logit Trojan Insertion (RLI) algorithm, uses smaller sampled test data instead of large training data to achieve the desired attack. The paper also introduces two additional techniques, namely the accumulated gradient ranking (AGR) and Trojan Weights Pruning (TWP), to reduce the number of tuned parameters and the attack overhead. The TrojText approach was evaluated on three datasets (AG's News, SST-2, and OLID) using three NLP models (BERT, XLNet, and DeBERTa). The experiments demonstrated that the TrojText approach achieved a 98.35\% classification accuracy for test sentences in the target class on the BERT model for the AG's News dataset. The source code for TrojText is available at https://github.com/UCF-ML-Research/TrojText.
Emerging self-supervised learning (SSL) has become a popular image representation encoding method to obviate the reliance on labeled data and learn rich representations from large-scale, ubiquitous unlabelled data. Then one can train a downstream classifier on top of the pre-trained SSL image encoder with few or no labeled downstream data. Although extensive works show that SSL has achieved remarkable and competitive performance on different downstream tasks, its security concerns, e.g, Trojan attacks in SSL encoders, are still not well-studied. In this work, we present a novel Trojan Attack method, denoted by ESTAS, that can enable an effective and stable attack in SSL encoders with only one target unlabeled sample. In particular, we propose consistent trigger poisoning and cascade optimization in ESTAS to improve attack efficacy and model accuracy, and eliminate the expensive target-class data sample extraction from large-scale disordered unlabelled data. Our substantial experiments on multiple datasets show that ESTAS stably achieves > 99% attacks success rate (ASR) with one target-class sample. Compared to prior works, ESTAS attains > 30% ASR increase and > 8.3% accuracy improvement on average.
Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple but unrealistic assumption. The parameters of a trained neural network model may affect task performance unevenly, which suggests non-equal importance among the parameters. Compared to SVD, the decomposition method aware of parameter importance is the more practical choice in real cases. Unlike standard SVD, weighted value decomposition is a non-convex optimization problem that lacks a closed-form solution. We systematically investigated multiple optimization strategies to tackle the problem and examined our method by compressing Transformer-based language models. Further, we designed a metric to predict when the SVD may introduce a significant performance drop, for which our method can be a rescue strategy. The extensive evaluations demonstrate that our method can perform better than current SOTA methods in compressing Transformer-based language models.
Performing neural network inference on encrypted data without decryption is one popular method to enable privacy-preserving neural networks (PNet) as a service. Compared with regular neural networks deployed for machine-learning-as-a-service, PNet requires additional encoding, e.g., quantized-precision numbers, and polynomial activation. Encrypted input also introduces novel challenges such as adversarial robustness and security. To the best of our knowledge, we are the first to study questions including (i) Whether PNet is more robust against adversarial inputs than regular neural networks? (ii) How to design a robust PNet given the encrypted input without decryption? We propose PNet-Attack to generate black-box adversarial examples that can successfully attack PNet in both target and untarget manners. The attack results show that PNet robustness against adversarial inputs needs to be improved. This is not a trivial task because the PNet model owner does not have access to the plaintext of the input values, which prevents the application of existing detection and defense methods such as input tuning, model normalization, and adversarial training. To tackle this challenge, we propose a new fast and accurate noise insertion method, called RPNet, to design Robust and Private Neural Networks. Our comprehensive experiments show that PNet-Attack reduces at least $2.5\times$ queries than prior works. We theoretically analyze our RPNet methods and demonstrate that RPNet can decrease $\sim 91.88\%$ attack success rate.
Vision Transformers (ViTs) have demonstrated the state-of-the-art performance in various vision-related tasks. The success of ViTs motivates adversaries to perform backdoor attacks on ViTs. Although the vulnerability of traditional CNNs to backdoor attacks is well-known, backdoor attacks on ViTs are seldom-studied. Compared to CNNs capturing pixel-wise local features by convolutions, ViTs extract global context information through patches and attentions. Na\"ively transplanting CNN-specific backdoor attacks to ViTs yields only a low clean data accuracy and a low attack success rate. In this paper, we propose a stealth and practical ViT-specific backdoor attack $TrojViT$. Rather than an area-wise trigger used by CNN-specific backdoor attacks, TrojViT generates a patch-wise trigger designed to build a Trojan composed of some vulnerable bits on the parameters of a ViT stored in DRAM memory through patch salience ranking and attention-target loss. TrojViT further uses minimum-tuned parameter update to reduce the bit number of the Trojan. Once the attacker inserts the Trojan into the ViT model by flipping the vulnerable bits, the ViT model still produces normal inference accuracy with benign inputs. But when the attacker embeds a trigger into an input, the ViT model is forced to classify the input to a predefined target class. We show that flipping only few vulnerable bits identified by TrojViT on a ViT model using the well-known RowHammer can transform the model into a backdoored one. We perform extensive experiments of multiple datasets on various ViT models. TrojViT can classify $99.64\%$ of test images to a target class by flipping $345$ bits on a ViT for ImageNet.
Factorizing a large matrix into small matrices is a popular strategy for model compression. Singular value decomposition (SVD) plays a vital role in this compression strategy, approximating a learned matrix with fewer parameters. However, SVD minimizes the squared error toward reconstructing the original matrix without gauging the importance of the parameters, potentially giving a larger reconstruction error for those who affect the task accuracy more. In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy. We analyze this previously unexplored problem, make observations, and address it by introducing Fisher information to weigh the importance of parameters affecting the model prediction. This idea leads to our method: Fisher-Weighted SVD (FWSVD). Although the factorized matrices from our approach do not result in smaller reconstruction errors, we find that our resulting task accuracy is much closer to the original model's performance. We perform analysis with the transformer-based language models, showing our weighted SVD largely alleviates the mismatched optimization objectives and can maintain model performance with a higher compression rate. Our method can directly compress a task-specific model while achieving better performance than other compact model strategies requiring expensive model pre-training. Moreover, the evaluation of compressing an already compact model shows our method can further reduce 9% to 30% parameters with an insignificant impact on task accuracy.