Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we define a realistic threat model, called user inference, wherein an attacker infers whether or not a user's data was used for fine-tuning. We implement attacks for this threat model that require only a small set of samples from a user (possibly different from the samples used for training) and black-box access to the fine-tuned LLM. We find that LLMs are susceptible to user inference attacks across a variety of fine-tuning datasets, at times with near perfect attack success rates. Further, we investigate which properties make users vulnerable to user inference, finding that outlier users (i.e. those with data distributions sufficiently different from other users) and users who contribute large quantities of data are most susceptible to attack. Finally, we explore several heuristics for mitigating privacy attacks. We find that interventions in the training algorithm, such as batch or per-example gradient clipping and early stopping fail to prevent user inference. However, limiting the number of fine-tuning samples from a single user can reduce attack effectiveness, albeit at the cost of reducing the total amount of fine-tuning data.
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an attacker seeks to determine whether a particular data sample was included in the training dataset of a model. Current state-of-the-art MI attacks capitalize on access to the model's predicted confidence scores to successfully perform membership inference, and employ data poisoning to further enhance their effectiveness. In this work, we focus on the less explored and more realistic label-only setting, where the model provides only the predicted label on a queried sample. We show that existing label-only MI attacks are ineffective at inferring membership in the low False Positive Rate (FPR) regime. To address this challenge, we propose a new attack Chameleon that leverages a novel adaptive data poisoning strategy and an efficient query selection method to achieve significantly more accurate membership inference than existing label-only attacks, especially at low FPRs.
Dropout is a common operator in deep learning, aiming to prevent overfitting by randomly dropping neurons during training. This paper introduces a new family of poisoning attacks against neural networks named DROPOUTATTACK. DROPOUTATTACK attacks the dropout operator by manipulating the selection of neurons to drop instead of selecting them uniformly at random. We design, implement, and evaluate four DROPOUTATTACK variants that cover a broad range of scenarios. These attacks can slow or stop training, destroy prediction accuracy of target classes, and sabotage either precision or recall of a target class. In our experiments of training a VGG-16 model on CIFAR-100, our attack can reduce the precision of the victim class by 34.6% (from 81.7% to 47.1%) without incurring any degradation in model accuracy
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to tampering only with the training data - without the ability to arbitrarily modify the training labels or any other component of the training process. We describe a trigger crafting strategy that leverages model interpretability techniques to generate trigger patterns that are effective even at very low poisoning rates. Finally, we design novel strategies to generate stealthy triggers, including an approach based on generative Bayesian network models, with the goal of minimizing the conspicuousness of the trigger, and thus making detection of an ongoing poisoning campaign more challenging. Our findings provide significant insights into the feasibility of poisoning attacks on network traffic classifiers used in multiple scenarios, including detecting malicious communication and application classification.
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially popular for privacy in machine learning, where the pretrained model is considered public, and only the data for finetuning is considered sensitive. However, there are reasons to believe that the data used for pretraining is still sensitive, making it essential to understand how much information the finetuned model leaks about the pretraining data. In this work we propose a new membership-inference threat model where the adversary only has access to the finetuned model and would like to infer the membership of the pretraining data. To realize this threat model, we implement a novel metaclassifier-based attack, TMI, that leverages the influence of memorized pretraining samples on predictions in the downstream task. We evaluate TMI on both vision and natural language tasks across multiple transfer learning settings, including finetuning with differential privacy. Through our evaluation, we find that TMI can successfully infer membership of pretraining examples using query access to the finetuned model.
We present a rigorous methodology for auditing differentially private machine learning algorithms by adding multiple carefully designed examples called canaries. We take a first principles approach based on three key components. First, we introduce Lifted Differential Privacy (LiDP) that expands the definition of differential privacy to handle randomized datasets. This gives us the freedom to design randomized canaries. Second, we audit LiDP by trying to distinguish between the model trained with $K$ canaries versus $K - 1$ canaries in the dataset, leaving one canary out. By drawing the canaries i.i.d., LiDP can leverage the symmetry in the design and reuse each privately trained model to run multiple statistical tests, one for each canary. Third, we introduce novel confidence intervals that take advantage of the multiple test statistics by adapting to the empirical higher-order correlations. Together, this new recipe demonstrates significant improvements in sample complexity, both theoretically and empirically, using synthetic and real data. Further, recent advances in designing stronger canaries can be readily incorporated into the new framework.
Privacy auditing techniques for differentially private (DP) algorithms are useful for estimating the privacy loss to compare against analytical bounds, or empirically measure privacy in settings where known analytical bounds on the DP loss are not tight. However, existing privacy auditing techniques usually make strong assumptions on the adversary (e.g., knowledge of intermediate model iterates or the training data distribution), are tailored to specific tasks and model architectures, and require retraining the model many times (typically on the order of thousands). These shortcomings make deploying such techniques at scale difficult in practice, especially in federated settings where model training can take days or weeks. In this work, we present a novel "one-shot" approach that can systematically address these challenges, allowing efficient auditing or estimation of the privacy loss of a model during the same, single training run used to fit model parameters. Our privacy auditing method for federated learning does not require a priori knowledge about the model architecture or task. We show that our method provides provably correct estimates for privacy loss under the Gaussian mechanism, and we demonstrate its performance on a well-established FL benchmark dataset under several adversarial models.
We study backdoor attacks in peer-to-peer federated learning systems on different graph topologies and datasets. We show that only 5% attacker nodes are sufficient to perform a backdoor attack with 42% attack success without decreasing the accuracy on clean data by more than 2%. We also demonstrate that the attack can be amplified by the attacker crashing a small number of nodes. We evaluate defenses proposed in the context of centralized federated learning and show they are ineffective in peer-to-peer settings. Finally, we propose a defense that mitigates the attacks by applying different clipping norms to the model updates received from peers and local model trained by a node.
Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on federated learning protocols that poison the data or the model. However, federated learning is a networked system where the communication between clients and server plays a critical role for the learning task performance. We highlight how communication introduces another vulnerability surface in federated learning and study the impact of network-level adversaries on training federated learning models. We show that attackers dropping the network traffic from carefully selected clients can significantly decrease model accuracy on a target population. Moreover, we show that a coordinated poisoning campaign from a few clients can amplify the dropping attacks. Finally, we develop a server-side defense which mitigates the impact of our attacks by identifying and up-sampling clients likely to positively contribute towards target accuracy. We comprehensively evaluate our attacks and defenses on three datasets, assuming encrypted communication channels and attackers with partial visibility of the network.
Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. Such attacks have privacy implications for data owners who share their datasets to train machine learning models. Several existing approaches for property inference attacks against deep neural networks have been proposed, but they all rely on the attacker training a large number of shadow models, which induces large computational overhead. In this paper, we consider the setting of property inference attacks in which the attacker can poison a subset of the training dataset and query the trained target model. Motivated by our theoretical analysis of model confidences under poisoning, we design an efficient property inference attack, SNAP, which obtains higher attack success and requires lower amounts of poisoning than the state-of-the-art poisoning-based property inference attack by Mahloujifar et al. For example, on the Census dataset, SNAP achieves 34% higher success rate than Mahloujifar et al. while being 56.5x faster. We also extend our attack to determine if a certain property is present at all in training, and estimate the exact proportion of a property of interest efficiently. We evaluate our attack on several properties of varying proportions from four datasets, and demonstrate SNAP's generality and effectiveness.