SoK: Unintended Interactions among Machine Learning Defenses and Risks

Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or decreased susceptibility to other risks. Existing research lacks an effective framework to recognize and explain these unintended interactions. We present such a framework, based on the conjecture that overfitting and memorization underlie unintended interactions. We survey existing literature on unintended interactions, accommodating them within our framework. We use our framework to conjecture on two previously unexplored interactions, and empirically validate our conjectures.

False Claims against Model Ownership Resolution

Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect against model theft. Model ownership resolution (MOR) is a class of techniques that can deter model theft. A MOR scheme enables an accuser to assert an ownership claim for a suspect model by presenting evidence, such as a watermark or fingerprint, to show that the suspect model was stolen or derived from a source model owned by the accuser. Most of the existing MOR schemes prioritize robustness against malicious suspects, ensuring that the accuser will win if the suspect model is indeed a stolen model. In this paper, we show that common MOR schemes in the literature are vulnerable to a different, equally important but insufficiently explored, robustness concern: a malicious accuser. We show how malicious accusers can successfully make false claims against independent suspect models that were not stolen. Our core idea is that a malicious accuser can deviate (without detection) from the specified MOR process by finding (transferable) adversarial examples that successfully serve as evidence against independent suspect models. To this end, we first generalize the procedures of common MOR schemes and show that, under this generalization, defending against false claims is as challenging as preventing (transferable) adversarial examples. Via systematic empirical evaluation we demonstrate that our false claim attacks always succeed in all prominent MOR schemes with realistic configurations, including against a real-world model: Amazon's Rekognition API.

On the Robustness of Dataset Inference

Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Thus, they constitute valuable intellectual property that needs protection from adversaries wanting to steal them. Ownership verification techniques allow the victims of model stealing attacks to demonstrate that a suspect model was in fact stolen from theirs. Although a number of ownership verification techniques based on watermarking or fingerprinting have been proposed, most of them fall short either in terms of security guarantees (well-equipped adversaries can evade verification) or computational cost. A fingerprinting technique introduced at ICLR '21, Dataset Inference (DI), has been shown to offer better robustness and efficiency than prior methods. The authors of DI provided a correctness proof for linear (suspect) models. However, in the same setting, we prove that DI suffers from high false positives (FPs) -- it can incorrectly identify an independent model trained with non-overlapping data from the same distribution as stolen. We further prove that DI also triggers FPs in realistic, non-linear suspect models. We then confirm empirically that DI leads to FPs, with high confidence. Second, we show that DI also suffers from false negatives (FNs) -- an adversary can fool DI by regularising a stolen model's decision boundaries using adversarial training, thereby leading to an FN. To this end, we demonstrate that DI fails to identify a model adversarially trained from a stolen dataset -- the setting where DI is the hardest to evade. Finally, we discuss the implications of our findings, the viability of fingerprinting-based ownership verification in general, and suggest directions for future work.

Conflicting Interactions Among Protections Mechanisms for Machine Learning Models

Nowadays, systems based on machine learning (ML) are widely used in different domains. Given their popularity, ML models have become targets for various attacks. As a result, research at the intersection of security and privacy, and ML has flourished. The research community has been exploring the attack vectors and potential mitigations separately. However, practitioners will likely need to deploy defences against several threats simultaneously. A solution that is optimal for a specific concern may interact negatively with solutions intended to address other concerns. In this work, we explore the potential for conflicting interactions between different solutions that enhance the security/privacy of ML-base systems. We focus on model and data ownership; exploring how ownership verification techniques interact with other ML security/privacy techniques like differentially private training, and robustness against model evasion. We provide a framework, and conduct systematic analysis of pairwise interactions. We show that many pairs are incompatible. Where possible, we provide relaxations to the hyperparameters or the techniques themselves that allow for the simultaneous deployment. Lastly, we discuss the implications and provide guidelines for future work.

SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning

Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an ML model, risk violating membership privacy. ML model builders need a principled definition of a metric that enables them to quantify the privacy risk of (a) individual training data records, (b) independently of specific MIAs, (c) efficiently. None of the prior work on membership privacy risk metrics simultaneously meets all of these criteria. We propose such a metric, SHAPr, which uses Shapley values to quantify a model's memorization of an individual training data record by measuring its influence on the model's utility. This memorization is a measure of the likelihood of a successful MIA. Using ten benchmark datasets, we show that SHAPr is effective (precision: 0.94$\pm 0.06$, recall: 0.88$\pm 0.06$) in estimating susceptibility of a training data record for MIAs, and is efficient (computable within minutes for smaller datasets and in ~90 minutes for the largest dataset). SHAPr is also versatile in that it can be used for other purposes like assessing fairness or assigning valuation for subsets of a dataset. For example, we show that SHAPr correctly captures the disproportionate vulnerability of different subgroups to MIAs. Using SHAPr, we show that the membership privacy risk of a dataset is not necessarily improved by removing high risk training data records, thereby confirming an observation from prior work in a significantly extended setting (in ten datasets, removing up to 50% of data).

Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks

Machine learning models are typically made available to potential client users via inference APIs. Model extraction attacks occur when a malicious client uses information gleaned from queries to the inference API of a victim model $F_V$ to build a surrogate model $F_A$ that has comparable functionality. Recent research has shown successful model extraction attacks against image classification, and NLP models. In this paper, we show the first model extraction attack against real-world generative adversarial network (GAN) image translation models. We present a framework for conducting model extraction attacks against image translation models, and show that the adversary can successfully extract functional surrogate models. The adversary is not required to know $F_V$'s architecture or any other information about it beyond its intended image translation task, and queries $F_V$'s inference interface using data drawn from the same domain as the training data for $F_V$. We evaluate the effectiveness of our attacks using three different instances of two popular categories of image translation: (1) Selfie-to-Anime and (2) Monet-to-Photo (image style transfer), and (3) Super-Resolution (super resolution). Using standard performance metrics for GANs, we show that our attacks are effective in each of the three cases -- the differences between $F_V$ and $F_A$, compared to the target are in the following ranges: Selfie-to-Anime: FID $13.36-68.66$, Monet-to-Photo: FID $3.57-4.40$, and Super-Resolution: SSIM: $0.06-0.08$ and PSNR: $1.43-4.46$. Furthermore, we conducted a large scale (125 participants) user study on Selfie-to-Anime and Monet-to-Photo to show that human perception of the images produced by the victim and surrogate models can be considered equivalent, within an equivalence bound of Cohen's $d=0.3$.

Extraction of Complex DNN Models: Real Threat or Boogeyman?

Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property (IP) of ML models has emerged as an important consideration. Confidentiality of ML models can be protected by exposing them to clients only via prediction APIs. However, model extraction attacks can steal the functionality of ML models using the information leaked to clients through the results returned via the API. In this work, we question whether model extraction is a serious threat to complex, real-life ML models. We evaluate the current state-of-the-art model extraction attack (the Knockoff attack) against complex models. We reproduced and confirm the results in the Knockoff attack paper. But we also show that the performance of this attack can be limited by several factors, including ML model architecture and the granularity of API response. Furthermore, we introduce a defense based on distinguishing queries used for Knockoff attack from benign queries. Despite the limitations of the Knockoff attack, we show that a more realistic adversary can effectively steal complex ML models and evade known defenses.

Detecting organized eCommerce fraud using scalable categorical clustering

Online retail, eCommerce, frequently falls victim to fraud conducted by malicious customers (fraudsters) who obtain goods or services through deception. Fraud coordinated by groups of professional fraudsters that place several fraudulent orders to maximize their gain is referred to as organized fraud. Existing approaches to fraud detection typically analyze orders in isolation and they are not effective at identifying groups of fraudulent orders linked to organized fraud. These also wrongly identify many legitimate orders as fraud, which hinders their usage for automated fraud cancellation. We introduce a novel solution to detect organized fraud by analyzing orders in bulk. Our approach is based on clustering and aims to group together fraudulent orders placed by the same group of fraudsters. It selectively uses two existing techniques, agglomerative clustering and sampling to recursively group orders into small clusters in a reasonable amount of time. We assess our clustering technique on real-world orders placed on the Zalando website, the largest online apparel retailer in Europe1. Our clustering processes 100,000s of orders in a few hours and groups 35-45% of fraudulent orders together. We propose a simple technique built on top of our clustering that detects 26.2% of fraud while raising false alarms for only 0.1% of legitimate orders.

DAWN: Dynamic Adversarial Watermarking of Neural Networks

Training machine learning (ML) models is expensive in terms of computational power, large amounts of labeled data, and human expertise. Thus, ML models constitute intellectual property (IP) and business value for their owners. Embedding digital watermarks during model training allows a model owner to later identify their models in case of theft or misuse. However, model functionality can also be stolen via model extraction, where an adversary trains a surrogate model using results returned from a prediction API of the original model. Recent work has shown that model extraction is a realistic threat. Existing watermarking schemes are ineffective against IP theft via model extraction since it is the adversary who trains the surrogate model. In this paper, we introduce DAWN (Dynamic Adversarial Watermarking of Neural Networks), the first approach to use watermarking to deter IP theft via model extraction. Unlike prior watermarking schemes, DAWN does not impose changes to the training process. Instead, it operates at the prediction API of the protected model, by dynamically changing the responses for a small subset of queries (e.g. $<0.5\%$) from API clients. This set represents a watermark that will be embedded in case a client uses its queries to train a surrogate model. We show that DAWN is resilient against two state-of-the-art model extraction attacks, effectively watermarking all extracted surrogate models, allowing model owners to reliably demonstrate ownership (with confidence $>1-2^{-64}$), incurring negligible loss of prediction accuracy ($0.03-0.5\%$).