Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair
Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina Păsăreanu
Neural networks are increasingly being deployed in contexts where safety is a critical concern.
In this work, we propose a way to construct neural network classifiers that dynamically repair violations of non-relational safety constraints called safe ordering properties.
Safe ordering properties relate requirements on the ordering of a network's output indices to conditions on their input, and are sufficient to express most useful notions of non-relational safety for classifiers.
Our approach is based on a novel self-repairing layer, which provably yields safe outputs regardless of the characteristics of its input.
We compose this layer with an existing network to construct a self-repairing network (SR-Net), and show that in addition to providing safe outputs, the SR-Net is guaranteed to preserve the accuracy of the original network.
Notably, our approach is independent of the size and architecture of the network being repaired, depending only on the specified property and the dimension of the network's output; thus it is scalable to large state-of-the-art networks.
We show that our approach can be implemented using vectorized computations that execute efficiently on a GPU, introducing run-time overhead of less than one millisecond on current hardware—even on large, widely-used networks containing hundreds of thousands of neurons and millions of parameters.
Relaxing Local Robustness [NIPS 2021]
Klas Leino, Matt Fredrikson
Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep learning. However, for some classification problems, local robustness is not a natural objective, even in the presence of adversaries; for example, if an image contains two classes of subjects, the correct label for the image may be considered arbitrary between the two, and thus enforcing strict separation between them is unnecessary. In this work, we introduce two relaxed safety properties for classifiers that address this observation: (1) relaxed top-k robustness, which serves as the analogue of top-k accuracy; and (2) affinity robustness, which specifies which sets of labels must be separated by a robustness margin, and which can be ε-close in ℓp space. We show how to construct models that can be efficiently certified against each relaxed robustness property, and trained with very little overhead relative to standard gradient descent. Finally, we demonstrate experimentally that these relaxed variants of robustness are well-suited to several significant classification problems, leading to lower rejection rates and higher certified accuracies than can be obtained when certifying "standard" local robustness.
Globally-Robust Neural Networks [ICML 2021]
Klas Leino, Zifan Wang, Matt Fredrikson
The threat of adversarial examples has motivated work on training certifiably robust neural networks, to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the operational properties of on-line local robustness certification while yielding a natural learning objective for robust training. We show that widely-used architectures can be easily adapted to this objective by incorporating efficient global Lipschitz bounds into the network, yielding certifiably-robust models by construction that achieve state-of-the-art verifiable accuracy. Notably, this approach requires significantly less time and memory than recent certifiable training methods, and leads to negligible costs when certifying points on-line; for example, our evaluation shows that it is possible to train a large tiny-imagenet model in a matter of hours. We posit that this is possible using inexpensive global bounds—despite prior suggestions that tighter local bounds are needed for good performance—because these models are trained to achieve tighter global bounds. Namely, we prove that the maximum achievable verifiable accuracy for a given dataset is not improved by using a local bound.
Fast Geometric Projections for Local Robustness Certification [ICLR 2021 - Spotlight]
Klas Leino*, Aymeric Fromherz*, Matt Fredrikson, Bryan Parno, Corina Păsăreanu
Local robustness ensures that a model classifies all inputs within an ε-ball consistently, which precludes various forms of adversarial inputs.
In this paper, we present a fast procedure for checking local robustness in feed-forward neural networks with piecewise linear activation functions.
The key insight is that such networks partition the input space into a polyhedral complex such that the network is linear inside each polyhedral region;
hence, a systematic search for decision boundaries within the regions around a given input is sufficient for assessing robustness.
Crucially, we show how these regions can be analyzed using geometric projections instead of expensive constraint solving, thus admitting an efficient, highly-parallel GPU implementation at the price of incompleteness, which can be addressed by falling back on prior approaches.
Empirically, we find that incompleteness is not often an issue, and that our method performs one to two orders of magnitude faster than existing robustness-certification techniques based on constraint solving.
Leveraging Model Memorization for Calibrated White-Box Membership Inference [USENIX 2020]
Klas Leino, Matt Fredrikson
Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model.
In this work, we study membership inference in the white-box setting in order to exploit the internals of a model, which have not been effectively utilized by previous work.
Leveraging new insights about how overfitting occurs in deep neural networks, we show how a model's idiosyncratic use of features can provide evidence of membership to white-box attackers—even when the model's black-box behavior appears to generalize well—and demonstrate that this approach outperforms prior black-box methods.
Taking the position that an effective attack should have the ability to provide confident positive inferences, we find that previous attacks do not often provide a meaningful basis for confidently inferring membership, whereas our attack can be effectively calibrated for high precision.
Finally, we examine popular defenses against MI attacks, finding that
(1) smaller generalization error is not sufficient to prevent attacks on real models, and
(2) while small-ε-differential privacy reduces the attack's effectiveness, this often comes at a significant cost to the model's accuracy; and for larger ε that are sometimes used in practice (e.g., ε = 16), the attack can achieve nearly the same accuracy as on the unprotected model.
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models [ACL 2020]
Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fedrikson, Anupam Datta
LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages such as subject-verb number agreement in English. Lacking this understanding, the generality of LSTMs on this task and their suitability for related tasks remains uncertain. Further, errors cannot be properly attributed to a lack of structural capability, training data omissions, or other exceptional faults. We introduce influence paths, a causal account of structural properties as carried by paths across gates and neurons of a recurrent neural network. The approach refines the notion of influence (the subject's grammatical number has influence on the grammatical number of the subsequent verb) into a set of gate-level or neuron-level paths. The set localizes and segments the concept (e.g., subject-verb agreement), its constituent elements (e.g., the subject), and related or interfering elements (e.g., attractors). We exemplify the methodology on a widely-studied multi-level LSTM language model, demonstrating its accounting for subject-verb number agreement. The results offer both a finer and a more complete view of an LSTM's handling of this structural aspect of the English language than prior results based on diagnostic classifiers and ablation.
Feature-wise Bias Amplification [ICLR 2019]
Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an inductive bias in gradient descent methods that results in the overestimation of the importance of moderately-predictive "weak" features if insufficient training data is available. This overestimation gives rise to feature-wise bias amplification — a previously unreported form of bias that can be traced back to the features of a trained model. Through analysis and experiments, we show that while some bias cannot be mitigated without sacrificing accuracy, feature-wise bias amplification can be mitigated through targeted feature selection. We present two new feature selection algorithms for mitigating bias amplification in linear models, and show how they can be adapted to convolutional neural networks efficiently. Our experiments on synthetic and real data demonstrate that these algorithms consistently lead to reduced bias without harming accuracy, in some cases eliminating predictive bias altogether while providing modest gains in accuracy.
Influence-directed Explanations for Convolutional Neural Networks [ITC 2018]
Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson
We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) can be used to extract the "essence" of what the network learned about a class, and (3) isolate individual features the network uses to make decisions and distinguish related classes.