The website fingerprinting attack allows a low-resource attacker to compromise the privacy guarantees provided by privacy enhancing tools such as Tor. In response, researchers have proposed defenses aimed at confusing the classification tools used by attackers. As new, more powerful attacks are frequently developed, raw attack accuracy has proven inadequate as the sole metric used to evaluate these defenses. In response, two security metrics have been proposed that allow for evaluating defenses based on hand-crafted features often used in attacks. Recent state-of-the-art attacks, however, use deep learning models capable of automatically learning abstract feature representations, and thus the proposed metrics fall short once again. In this study we examine two security metrics and (1) show how these methods can be extended to evaluate deep learning-based website fingerprinting attacks, and (2) compare the security metrics and identify their shortcomings.
more »
« less
Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems
Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performance metrics (e.g., desired accuracy, latency). The server maintains a set of models (model zoo) in the back-end and serves the queries based on the specified metrics. This paper examines the security, specifically robustness against model extraction attacks, of such systems. Existing black-box attacks assume a single model can be repeatedly selected for serving inference requests. Modern inference serving systems break this assumption. Thus, they cannot be directly applied to extract a victim model, as models are hidden behind a layer of abstraction exposed by the serving system. An attacker can no longer identify which model she is interacting with. To this end, we first propose a query-efficient fingerprinting algorithm to enable the attacker to trigger any desired model consistently. We show that by using our fingerprinting algorithm, model extraction can have fidelity and accuracy scores within 1% of the scores obtained when attacking a single, explicitly specified model, as well as up to 14.6% gain in accuracy and up to 7.7% gain in fidelity compared to the naive attack. Second, we counter the proposed attack with a noise-based defense mechanism that thwarts fingerprinting by adding noise to the specified performance metrics. The proposed defense strategy reduces the attack's accuracy and fidelity by up to 9.8% and 4.8%, respectively (on medium-sized model extraction). Third, we show that the proposed defense induces a fundamental trade-off between the level of protection and system goodput, achieving configurable and significant victim model extraction protection while maintaining acceptable goodput (>80%). We implement the proposed defense in a real system with plans to open source.
more »
« less
- Award ID(s):
- 2246937
- PAR ID:
- 10524683
- Publisher / Repository:
- cs.ArXiv
- Date Published:
- Subject(s) / Keyword(s):
- psml machine learning security Pareto-secure machine learning inference indistinguishability differential privacy
- Format(s):
- Medium: X
- Location:
- cs.ArXiv
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise privacy concerns such as model extraction. In model extraction attacks, adversaries mali- ciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or propri- etary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramèr et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that re- cent advancements in the active learning domain can be used to imple- ment powerful model extraction attacks, and investigate possible defense strategies.more » « less
-
Machine learning is being increasingly used by individu- als, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise concerns such as model extraction. In model extraction attacks, adversaries maliciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approxi- mation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramèr et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that recent advancements in the active learning domain can be used to implement powerful model extraction attacks, and investigate possible defense strategies.more » « less
-
Recent model-extraction attacks on Machine Learning as a Service (MLaaS) systems have moved towards data-free approaches, showing the feasibility of stealing models trained with difficult-to-access data. However, these attacks are ineffective or limited due to the low accuracy of extracted models and the high number of queries to the models under attack. The high query cost makes such techniques infeasible for online MLaaS systems that charge per query.We create a novel approach to get higher accuracy and query efficiency than prior data-free model extraction techniques. Specifically, we introduce a novel generator training scheme that maximizes the disagreement loss between two clone models that attempt to copy the model under attack. This loss, combined with diversity loss and experience replay, enables the generator to produce better instances to train the clone models. Our evaluation on popular datasets CIFAR-10 and CIFAR-100 shows that our approach improves the final model accuracy by up to 3.42% and 18.48% respectively. The average number of queries required to achieve the accuracy of the prior state of the art is reduced by up to 64.95%. We hope this will promote future work on feasible data-free model extraction and defenses against such attacks.more » « less
-
With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on deep networks where the attacker provides poisoned data to the victim to train the model with, and then activates the attack by showing a specific small trigger pattern at the test time. Most state-of-the-art backdoor attacks either provide mislabeled poisoning data that is possible to identify by visual inspection, reveal the trigger in the poisoned data, or use noise to hide the trigger. We propose a novel form of backdoor attack where poisoned data look natural with correct labels and also more importantly, the attacker hides the trigger in the poisoned data and keeps the trigger secret until the test time. We perform an extensive study on various image classification settings and show that our attack can fool the model by pasting the trigger at random locations on unseen images although the model performs well on clean data. We also show that our proposed attack cannot be easily defended using a state-of-the-art defense algorithm for backdoor attacks.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
