Robert Stanforth

Sahra Ghalebikesabi, Eugene Bagdasaryan, Ren Yi et al. · deepmind

Advanced AI assistants combine frontier LLMs and tool access to autonomously perform complex tasks on behalf of users. While the helpfulness of such assistants can increase dramatically with access to user information including emails and documents, this raises privacy concerns about assistants sharing inappropriate information with third parties without user supervision. To steer information-sharing assistants to behave in accordance with privacy expectations, we propose to operationalize contextual integrity (CI), a framework that equates privacy with the appropriate flow of information in a given context. In particular, we design and evaluate a number of strategies to steer assistants' information-sharing actions to be CI compliant. Our evaluation is based on a novel form filling benchmark composed of human annotations of common webform applications, and it reveals that prompting frontier LLMs to perform CI-based reasoning yields strong results.

Leonard Berrada, Soham De, Judy Hanwen Shen et al. · deepmind, stanford

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework for privacy-preserving training, as it provides formal privacy guarantees. However, compared to their non-private counterparts, models trained with DP often have significantly reduced accuracy. Private classifiers are also believed to exhibit larger performance disparities across subpopulations, raising fairness concerns. The poor performance of classifiers trained with DP has prevented the widespread adoption of privacy preserving machine learning in industry. Here we show that pre-trained foundation models fine-tuned with DP can achieve similar accuracy to non-private classifiers, even in the presence of significant distribution shifts between pre-training data and downstream tasks. We achieve private accuracies within a few percent of the non-private state of the art across four datasets, including two medical imaging benchmarks. Furthermore, our private medical classifiers do not exhibit larger performance disparities across demographic groups than non-private models. This milestone to make DP training a practical and reliable technology has the potential to widely enable machine learning practitioners to train safely on sensitive datasets while protecting individuals' privacy.

Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal et al. · deepmind

The ability to generate privacy-preserving synthetic versions of sensitive image datasets could unlock numerous ML applications currently constrained by data availability. Due to their astonishing image generation quality, diffusion models are a prime candidate for generating high-quality synthetic data. However, recent studies have found that, by default, the outputs of some diffusion models do not preserve training data privacy. By privately fine-tuning ImageNet pre-trained diffusion models with more than 80M parameters, we obtain SOTA results on CIFAR-10 and Camelyon17 in terms of both FID and the accuracy of downstream classifiers trained on synthetic data. We decrease the SOTA FID on CIFAR-10 from 26.2 to 9.8, and increase the accuracy from 51.0% to 88.0%. On synthetic data from Camelyon17, we achieve a downstream accuracy of 91.1% which is close to the SOTA of 96.5% when training on the real data. We leverage the ability of generative models to create infinite amounts of data to maximise the downstream prediction performance, and further show how to use synthetic data for hyperparameter tuning. Our results demonstrate that diffusion models fine-tuned with differential privacy can produce useful and provably private synthetic data, even in applications with significant distribution shift between the pre-training and fine-tuning distributions.

Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham et al.

Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding various regularization terms to the objective. However, these algorithms either underperform or require complex and expensive stage-wise training procedures, hindering their practical applicability. We present IBP-R, a novel verified training algorithm that is both simple and effective. IBP-R induces network verifiability by coupling adversarial attacks on enlarged domains with a regularization term, based on inexpensive interval bound propagation, that minimizes the gap between the non-convex verification problem and its approximations. By leveraging recent branch-and-bound frameworks, we show that IBP-R obtains state-of-the-art verified robustness-accuracy trade-offs for small perturbations on CIFAR-10 while training significantly faster than relevant previous work. Additionally, we present UPB, a novel branching strategy that, relying on a simple heuristic based on $β$-CROWN, reduces the cost of state-of-the-art branching algorithms while yielding splits of comparable quality.

Huan Zhang, Hongge Chen, Chaowei Xiao et al.

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanwhile, interval bound propagation (IBP) based training is efficient and significantly outperforms linear relaxation based methods on many tasks, yet it may suffer from stability issues since the bounds are much looser especially at the beginning of training. In this paper, we propose a new certified adversarial training method, CROWN-IBP, by combining the fast IBP bounds in a forward bounding pass and a tight linear relaxation based bound, CROWN, in a backward bounding pass. CROWN-IBP is computationally efficient and consistently outperforms IBP baselines on training verifiably robust neural networks. We conduct large scale experiments on MNIST and CIFAR datasets, and outperform all previous linear relaxation and bound propagation based certified defenses in $\ell_\infty$ robustness. Notably, we achieve 7.02% verified test error on MNIST at $ε=0.3$, and 66.94% on CIFAR-10 with $ε=8/255$. Code is available at https://github.com/deepmind/interval-bound-propagation (TensorFlow) and https://github.com/huanzhang12/CROWN-IBP (PyTorch).

Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar et al. · deepmind

We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verification algorithm without any human input. Prior work on neural network verification has focused on partial specifications that, even when satisfied, are not sufficient to ensure that a neural network never makes errors. We focus on applying neural network verification to computational tasks with a precise notion of correctness, where a verifiably correct neural network provably solves the task at hand with no caveats. In particular, we develop an approach to train and verify the first provably correct neural networks for compressed sensing, i.e., recovering sparse vectors from a number of measurements smaller than the dimension of the vector. We show that for modest problem dimensions (up to 50), we can train neural networks that provably recover a sparse vector from linear and binarized linear measurements. Furthermore, we show that the complexity of the network (number of neurons/layers) can be adapted to the problem difficulty and solve problems where traditional compressed sensing methods are not known to provably work.

Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham et al.

In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance. As shown in recent work, better trade-offs between accuracy and robustness can be obtained by carefully coupling adversarial training with over-approximations. We hypothesize that the expressivity of a loss function, which we formalize as the ability to span a range of trade-offs between lower and upper bounds to the worst-case loss through a single parameter (the over-approximation coefficient), is key to attaining state-of-the-art performance. To support our hypothesis, we show that trivial expressive losses, obtained via convex combinations between adversarial attacks and IBP bounds, yield state-of-the-art results across a variety of settings in spite of their conceptual simplicity. We provide a detailed analysis of the relationship between the over-approximation coefficient and performance profiles across different expressive losses, showing that, while expressivity is essential, better approximations of the worst-case loss are not necessarily linked to superior robustness-accuracy trade-offs.

Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham et al.

Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabilistic. Despite the promise of formal verification in ensuring the reliability of neural networks, progress in the direction of probabilistic specifications has been limited. In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic networks (e.g., Bayesian neural networks, MC-Dropout networks) and uncertain inputs (distributions over inputs arising from sensor noise or other perturbations). We then propose a general technique to verify such specifications by generalizing the notion of Lagrangian duality, replacing standard Lagrangian multipliers with "functional multipliers" that can be arbitrary functions of the activations at a given layer. We show that an optimal choice of functional multipliers leads to exact verification (i.e., sound and complete verification), and for specific forms of multipliers, we develop tractable practical verification algorithms. We empirically validate our algorithms by applying them to Bayesian Neural Networks (BNNs) and MC Dropout Networks, and certifying properties such as adversarial robustness and robust detection of out-of-distribution (OOD) data. On these tasks we are able to provide significantly stronger guarantees when compared to prior work -- for instance, for a VGG-64 MC-Dropout CNN trained on CIFAR-10, we improve the certified AUC (a verified lower bound on the true AUC) for robust OOD detection (on CIFAR-100) from $0\% \rightarrow 29\%$. Similarly, for a BNN trained on MNIST, we improve on the robust accuracy from $60.2\% \rightarrow 74.6\%$. Further, on a novel specification -- distributionally robust OOD detection -- we improve the certified AUC from $5\% \rightarrow 23\%$.

Jim Winkens, Rudy Bunel, Abhijit Guha Roy et al.

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

Po-Sen Huang, Huan Zhang, Ray Jiang et al.

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to internalize social biases present in the training corpus. This paper aims to quantify and reduce a particular type of bias exhibited by language models: bias in the sentiment of generated text. Given a conditioning context (e.g., a writing prompt) and a language model, we analyze if (and how) the sentiment of the generated text is affected by changes in values of sensitive attributes (e.g., country names, occupations, genders) in the conditioning context using a form of counterfactual evaluation. We quantify sentiment bias by adopting individual and group fairness metrics from the fair machine learning literature, and demonstrate that large-scale models trained on two different corpora (news articles, and Wikipedia) exhibit considerable levels of bias. We then propose embedding and sentiment prediction-derived regularization on the language model's latent representations. The regularizations improve fairness metrics while retaining comparable levels of perplexity and semantic similarity.

Po-Sen Huang, Robert Stanforth, Johannes Welbl et al.

Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such brittleness, but these are unlikely to find worst-case adversaries due to the complexity of the search space arising from discrete text perturbations. In this work, we approach the problem from the opposite direction: to formally verify a system's robustness against a predefined class of adversarial attacks. We study text classification under synonym replacements or character flip perturbations. We propose modeling these input perturbations as a simplex and then using Interval Bound Propagation -- a formal model verification method. We modify the conventional log-likelihood training objective to train models that can be efficiently verified, which would otherwise come with exponential search complexity. The resulting models show only little difference in terms of nominal accuracy, but have much improved verified accuracy under perturbations and come with an efficiently computable formal guarantee on worst case adversaries.

Chongli Qin, James Martens, Sven Gowal et al.

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of the model and number of input dimensions increase. Further, training against less expensive and therefore weaker adversaries produces models that are robust against weak attacks but break down under attacks that are stronger. This is often attributed to the phenomenon of gradient obfuscation; such models have a highly non-linear loss surface in the vicinity of training examples, making it hard for gradient-based attacks to succeed even though adversarial examples still exist. In this work, we introduce a novel regularizer that encourages the loss to behave linearly in the vicinity of the training data, thereby penalizing gradient obfuscation while encouraging robustness. We show via extensive experiments on CIFAR-10 and ImageNet, that models trained with our regularizer avoid gradient obfuscation and can be trained significantly faster than adversarial training. Using this regularizer, we exceed current state of the art and achieve 47% adversarial accuracy for ImageNet with l-infinity adversarial perturbations of radius 4/255 under an untargeted, strong, white-box attack. Additionally, we match state of the art results for CIFAR-10 at 8/255.

Jonathan Uesato, Jean-Baptiste Alayrac, Po-Sen Huang et al.

Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This result is a key hurdle in the deployment of robust machine learning models in many real world applications where labeled data is expensive. Our main insight is that unlabeled data can be a competitive alternative to labeled data for training adversarially robust models. Theoretically, we show that in a simple statistical setting, the sample complexity for learning an adversarially robust model from unlabeled data matches the fully supervised case up to constant factors. On standard datasets like CIFAR-10, a simple Unsupervised Adversarial Training (UAT) approach using unlabeled data improves robust accuracy by 21.7% over using 4K supervised examples alone, and captures over 95% of the improvement from the same number of labeled examples. Finally, we report an improvement of 4% over the previous state-of-the-art on CIFAR-10 against the strongest known attack by using additional unlabeled data from the uncurated 80 Million Tiny Images dataset. This demonstrates that our finding extends as well to the more realistic case where unlabeled data is also uncurated, therefore opening a new avenue for improving adversarial training.

Chongli Qin, Krishnamurthy, Dvijotham et al.

Prior work on neural network verification has focused on specifications that are linear functions of the output of the network, e.g., invariance of the classifier output under adversarial perturbations of the input. In this paper, we extend verification algorithms to be able to certify richer properties of neural networks. To do this we introduce the class of convex-relaxable specifications, which constitute nonlinear specifications that can be verified using a convex relaxation. We show that a number of important properties of interest can be modeled within this class, including conservation of energy in a learned dynamics model of a physical system; semantic consistency of a classifier's output labels under adversarial perturbations and bounding errors in a system that predicts the summation of handwritten digits. Our experimental evaluation shows that our method is able to effectively verify these specifications. Moreover, our evaluation exposes the failure modes in models which cannot be verified to satisfy these specifications. Thus, emphasizing the importance of training models not just to fit training data but also to be consistent with specifications.

Edward Grefenstette, Robert Stanforth, Brendan O'Donoghue et al.

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can make the models produce extremely inaccurate outputs. This makes these models particularly unsuitable for safety-critical application domains (e.g. self-driving cars) where robustness is extremely important. Recent work has shown that augmenting training with adversarially generated data provides some degree of robustness against test-time attacks. In this paper we investigate how this approach scales as we increase the computational budget given to the defender. We show that increasing the number of parameters in adversarially-trained models increases their robustness, and in particular that ensembling smaller models while adversarially training the entire ensemble as a single model is a more efficient way of spending said budget than simply using a larger single model. Crucially, we show that it is the adversarial training of the ensemble, rather than the ensembling of adversarially trained models, which provides robustness.

Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth et al.

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often result in difficult optimization procedures that remain hard to scale to larger networks. Through a comprehensive analysis, we show how a simple bounding technique, interval bound propagation (IBP), can be exploited to train large provably robust neural networks that beat the state-of-the-art in verified accuracy. While the upper bound computed by IBP can be quite weak for general networks, we demonstrate that an appropriate loss and clever hyper-parameter schedule allow the network to adapt such that the IBP bound is tight. This results in a fast and stable learning algorithm that outperforms more sophisticated methods and achieves state-of-the-art results on MNIST, CIFAR-10 and SVHN. It also allows us to train the largest model to be verified beyond vacuous bounds on a downscaled version of ImageNet.

Krishnamurthy Dvijotham, Sven Gowal, Robert Stanforth et al.

This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i.e., networks that provably satisfy some desired input-output properties. The key idea is to simultaneously train two networks: a predictor network that performs the task at hand,e.g., predicting labels given inputs, and a verifier network that computes a bound on how well the predictor satisfies the properties being verified. Both networks can be trained simultaneously to optimize a weighted combination of the standard data-fitting loss and a term that bounds the maximum violation of the property. Experiments show that not only is the predictor-verifier architecture able to train networks to achieve state of the art verified robustness to adversarial examples with much shorter training times (outperforming previous algorithms on small datasets like MNIST and SVHN), but it can also be scaled to produce the first known (to the best of our knowledge) verifiably robust networks for CIFAR-10.

Krishnamurthy, Dvijotham, Robert Stanforth et al.

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that neural networks satisfy specifications relating their inputs and outputs (robustness to bounded norm adversarial perturbations, for example). Most previous work on this topic was limited in its applicability by the size of the network, network architecture and the complexity of properties to be verified. In contrast, our framework applies to a general class of activation functions and specifications on neural network inputs and outputs. We formulate verification as an optimization problem (seeking to find the largest violation of the specification) and solve a Lagrangian relaxation of the optimization problem to obtain an upper bound on the worst case violation of the specification being verified. Our approach is anytime i.e. it can be stopped at any time and a valid bound on the maximum violation can be obtained. We develop specialized verification algorithms with provable tightness guarantees under special assumptions and demonstrate the practical significance of our general verification approach on a variety of verification tasks.