Large Language Models (LLMs) are vulnerable to **jailbreaking attacks** that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial prompt generation often leads to semantically meaningless attacks that do not scale well. In this paper, we present a novel method that uses another LLM, called **AdvPrompter**, to generate human-readable adversarial prompts in seconds. AdvPrompter, which is trained using an alternating optimization algorithm, generates suffixes that veil the input instruction without changing its meaning, such that the TargetLLM is lured to give a harmful response. Experimental results on popular open source TargetLLM show highly competitive results on the AdvBench and HarmBench datasets, that also transfer to closed-source black-box LLMs. We also show that training on adversarial suffixes generated by AdvPrompter is a promising strategy for improving the robustness of LLMs to jailbreaking attacks.

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is exacerbated by the agent's ability to take action on their user's behalf. Existing tests for prompt injections in web agents either over-simplify the threat by testing unrealistic scenarios or giving the attacker too much power, or look at single-step isolated tasks. To more accurately measure progress for secure web agents, we introduce WASP – a new publicly available benchmark for end-to-end evaluation of Web Agent Security against Prompt Injection attacks. Evaluating with WASP shows that even top-tier AI models, including those with advanced reasoning capabilities, can be deceived by simple, low-effort human-written injections in very realistic scenarios. Our end-to-end evaluation reveals a previously unobserved insight: while attacks partially succeed in up to 86% of the case, even state-of-the-art agents often struggle to fully complete the attacker goals – highlighting the current state of security by incompetence. Code and data are available at https://github.com/facebookresearch/wasp.

Conventional wisdom in machine learning privacy research states that memorization directly implies a loss of privacy. In contrast, a well-generalized model only remembers distributional patterns and preserves privacy of its training data. In this work, we show that this relationship is much more complex for LLMs trained for chat, and depends heavily on how knowledge is encoded and manipulated. To this end, we fine-tune language models on synthetically generated biographical information including PIIs, and try to extract them in different ways after instruction fine-tuning. We find counter to conventional wisdom that better verbatim memorization does not necessarily increase data leakage via chat. We also find that it is easier to extract information via chat from an LLM that is better able to manipulate and process knowledge even if it is smaller, and that not all attributes are equally extractable. This suggests that the relationship between privacy, memorization and language understanding of LLMs is very intricate, and that examining memorization in isolation can lead to misleading conclusions.

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their users, raising the question of whether they are capable of using it appropriately. In this work, we introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of "data minimization". For the purposes of our benchmark, data minimization means that the agent uses a piece of potentially sensitive information only if it is "necessary" to complete a particular task. Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents. We use AgentDAM to evaluate how well AI agents built on top of GPT-4, Llama-3 and Claude can limit processing of potentially private information, and show that they are prone to inadvertent use of unnecessary sensitive information. We also propose a prompting-based defense that reduces information leakage, and demonstrate that our end-to-end benchmarking provides a more realistic measure than probing LLMs about privacy. Our results highlight that further research is needed to develop AI agents that can prioritize data minimization at inference time. We open source our benchmark at: https://github.com/facebookresearch/ai-agent-privacy

Many jailbreak attacks on large language models (LLMs) rely on a common objective: making the model respond with the prefix ``Sure, here is (harmful request)''. While straightforward, this objective has two limitations: limited control over model behaviors, yielding incomplete or unrealistic jailbroken responses, and a rigid format that hinders optimization. We introduce AdvPrefix, a plug-and-play prefix-forcing objective that selects one or more model-dependent prefixes by combining two criteria: high prefilling attack success rates and low negative log-likelihood. AdvPrefix integrates seamlessly into existing jailbreak attacks to mitigate the previous limitations for free. For example, replacing GCG's default prefixes on Llama-3 improves nuanced attack success rates from 14\% to 80\%, revealing that current safety alignment fails to generalize to new prefixes. Code and selected prefixes are released.

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use cases can result in unnecessary degradation of utility. In this work, we refine the definition of DP to create a more general and flexible framework that we call feature differential privacy (FDP). Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary and adaptive separation of protected and non-protected features. We prove the properties of FDP, such as adaptive composition, and demonstrate its implications for limiting attribute inference attacks. We also propose a modification of the standard DP-SGD algorithm that satisfies FDP while leveraging desirable properties such as amplification via sub-sampling. We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available. For example, we train diffusion models on the AFHQ dataset of animal faces and observe a drastic improvement in FID compared to DP, from 286.7 to 101.9 at ∊ = 8, assuming that the blurred version of a training image is available as a public feature. Overall, our work provides a new approach to private data analysis that can help reduce the utility cost of DP while still providing strong privacy guarantees.

Differentially private (DP) machine learning is considered the gold-standard solution for training a model from sensitive data while still preserving privacy. However, a major barrier to achieving this ideal is its sub-optimal privacy-accuracy trade-off, which is particularly visible in DP representation learning. Specifically, it has been shown that under modest privacy budgets, most models learn representations that are not significantly better than hand-crafted features. In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets. Through a series of engineering tricks, we successfully train a DP image captioner (DP-Cap) on a 233M subset of LAION-2B from scratch using a reasonable amount of computation, and obtaining unprecedented high-quality image features that can be used in a variety of downstream vision and vision-language tasks. For example, under a privacy budget of $\varepsilon=8$ for the LAION dataset, a linear classifier trained on top of learned DP-Cap features attains $65.8\%$ accuracy on ImageNet-1K, considerably improving the previous SOTA of $56.5\%$. Our work challenges the prevailing sentiment that high-utility DP representation learning cannot be achieved by training from scratch.

Artificial intelligence (AI) has seen a tremendous surge in capabilities thanks to the use of foundation models trained on internet-scale data. On the flip side, the uncurated nature of internet-scale data also poses significant privacy and legal risks, as they often contain personal information or copyrighted material that should not be trained on without permission. In this work, we propose as a mitigation measure a recipe to train foundation vision models via self-supervised learning with differential privacy (DP) guarantee. We identify masked autoencoders as a suitable learning algorithm that aligns well with DP-SGD, and train *ViP*---a **Vi**sion transformer with differential **P**rivacy---under a strict privacy budget of $\epsilon=8$ on the LAION400M dataset. We evaluate the quality of representation learned by ViP using standard downstream vision tasks; in particular, ViP achieves a (non-private) linear probing accuracy of 55.7% on ImageNet, comparable to that of end-to-end trained AlexNet (trained and evaluated on ImageNet). Our result suggests that scaling to internet-scale data can be practical for private learning. Code and DP pre-trained models are available at https://github.com/facebookresearch/ViP-MAE.

Vision-Language Models (VLMs) have emerged as the state-of-the-art representation learning solution, with myriads of downstream applications such as image classification, retrieval and generation. A natural question is whether these models memorize their training data, which also has implications for generalization. We propose a new method for measuring memorization in VLMs, which we call dèjá vu memorization. For VLMs trained on image-caption pairs, we show that the model indeed retains information about individual objects in the training images beyond what can be inferred from correlations or the image caption. We evaluate dèjá vu memorization at both sample and population level, and show that it is significant for OpenCLIP trained on as many as 50M image-caption pairs. Finally, we show that text randomization considerably mitigates memorization risk while only moderately impacting the model’s downstream task performance. The code is available here: https://github.com/facebookresearch/VLMDejaVu.

Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation learning models and training images, it is sometimes possible to correctly predict the foreground label given only the representation of he background – better than through dataset-level correlations. However, their measurement method requires training two models – one to estimate dataset-level correlations and the other to estimate memorization. This multiple model setup becomes infeasible for large open-source models. In this work, we propose alter native simple methods to estimate dataset-level correlations, and show that these can be used to approximate an off-the-shelf model’s memorization ability without any retraining. This enables, for the first time, the measurement of memorization in pre-trained open-source image representation and vision-language models. Our results show that different ways of measuring memorization yield very similar aggregate results. We also find that open-source models typically have lower aggregate memorization than similar models trained on a subset of the data. The code is available both for vision (https://github.com/facebookresearch/DejaVuOSS) and vision language (https://github.com/facebookresearch/VLMDejaVu) models.

Machine learning models are known to be susceptible to adversarial perturbations. Even more concerning is the fact that these adversarial perturbations can be found by black-box search using surprisingly few queries, which essentially restricts the perturbation to a subspace of dimension $k$—much smaller than the dimension $d$ of the image space. This intriguing phenomenon raises the question: Is the vulnerability to black-box attacks inherent or can we hope to prevent them? In this paper, we initiate a rigorous study of the phenomenon of low-dimensional adversarial perturbations (LDAPs). Our result characterizes precisely the sufficient conditions for the existence of LDAPs, and we show that these conditions hold for neural networks under practical settings, including the so-called lazy regime wherein the parameters of the trained network remain close to their values at initialization. Our theoretical results are confirmed by experiments on both synthetic and real data.

Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels. Despite its rigorous privacy guarantee, it has been observed that in practice label-DP does not preclude label inference attacks (LIAs): Models trained with label-DP can be evaluated on the public training features to recover, with high accuracy, the very private labels that it was designed to protect. In this work, we argue that this phenomenon is not paradoxical and that label-DP is designed to limit the advantage of an LIA adversary compared to predicting training labels using the Bayes classifier. At label-DP $\epsilon=0$ this advantage is zero, hence the optimal attack is to predict according to the Bayes classifier and is independent of the training labels. Our bound shows the semantic protection conferred by label-DP and gives guidelines on how to choose $\epsilon$ to limit the threat of LIAs below a certain level. Finally, we empirically demonstrate that our result closely captures the behavior of simulated attacks on both synthetic and real world datasets.

In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model. The main challenge in this setting is balancing privacy with both classification accuracy of the learnt model as well as the number of bits communicated between the clients and server. Prior work has achieved a good trade-off by designing a privacy-aware compression mechanism, called the minimum variance unbiased (MVU) mechanism, that numerically solves an optimization problem to determine the parameters of the mechanism. This paper builds upon it by introducing a new interpolation procedure in the numerical design process that allows for a far more efficient privacy analysis. The result is the new Interpolated MVU mechanism that is more scalable, has a better privacy-utility trade-off, and provides SOTA results on communication-efficient private FL on a variety of datasets.

Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning. However, exactly how small the privacy parameter $\epsilon$ needs to be to protect against certain privacy risks in practice is still not well-understood. In this work, we study data reconstruction attacks for discrete data and analyze it under the framework of multiple hypothesis testing. For a learning algorithm satisfying $(\alpha, \epsilon)$-Renyi DP, we utilize different variants of the celebrated Fano’s inequality to upper bound the attack advantage of a data reconstruction adversary. Our bound can be numerically computed to relate the parameter $\epsilon$ to the desired level of privacy protection in practice, and complements the empirical evidence for the effectiveness of DP against data reconstruction attacks even at relatively large values of $\epsilon$.

Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners. To this end, FL requires the data owners to perform training locally and share the gradients or weight updates (instead of the private inputs) with the central server, which are then securely aggregated over multiple data owners. Although aggregation by itself does not offer provable privacy protection, prior work suggested that if the batch size is sufficiently large the aggregation may be secure enough. In this paper, we propose the Cocktail Party Attack (CPA) that, contrary to prior belief, is able to recover the private inputs from gradients/weight updates aggregated over as many as 1024 samples. CPA leverages the crucial insight that aggregate gradients from a fully connected (FC) layer is a linear combination of its inputs, which allows us to frame gradient inversion as a blind source separation (BSS) problem. We adapt independent component analysis (ICA)—a classic solution to the BSS problem—to recover private inputs for FC and convolutional networks, and show that CPA significantly outperforms prior gradient inversion attacks, scales to ImageNet-sized inputs, and works on large batch sizes of up to 1024.

Privacy-preserving instance encoding aims to encode raw data into feature vectors without revealing their privacy-sensitive information. When designed properly, these encodings can be used for downstream ML applications such as training and inference with limited privacy risk. However, the vast majority of existing schemes do not theoretically justify that their encoding is non-invertible, and their privacy-enhancing properties are only validated empirically against a limited set of attacks. In this paper, we propose a theoretically-principled measure for the invertibility of instance encoding based on Fisher information that is broadly applicable to a wide range of popular encoders. We show that dFIL can be used to bound the invertibility of encodings both theoretically and empirically, providing an intuitive interpretation of the privacy of instance encoding.

Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural images with one another. However, when taken to the extreme, SSL models can unintendedly memorize specific parts in individual training samples rather than learning semantically meaningful associations. In this work, we perform a systematic study of the unintended memorization of image-specific information in SSL models -- which we refer to as déjà vu memorization. Concretely, we show that given the trained model and a crop of a training image containing only the background (e.g., water, sky, grass), it is possible to infer the foreground object with high accuracy or even visually reconstruct it. Furthermore, we show that déjà vu memorization is common to different SSL algorithms, is exacerbated by certain design choices, and cannot be detected by conventional techniques for evaluating representation quality. Our study of déjà vu memorization reveals previously unknown privacy risks in SSL models, as well as suggests potential practical mitigation strategies.

Most existing approaches of differentially private (DP) machine learning focus on private training. Despite its many advantages, private training lacks the flexibility in adapting to incremental changes to the training dataset such as deletion requests from exercising GDPR’s right to be forgotten. We revisit a long-forgotten alternative, known as private prediction, and propose a new algorithm named Individual Kernelized Nearest Neighbor (Ind-KNN). Ind-KNN is easily updatable over dataset changes and it allows precise control of the Rényi DP at an individual user level — a user’s privacy loss is measured by the exact amount of her contribution to predictions; and a user is removed if her prescribed privacy budget runs out. Our results show that Ind-KNN consistently improves the accuracy over existing private prediction methods for a wide range of epsilon on four vision and language tasks. We also illustrate several cases under which Ind-KNN is preferable over private training with NoisySGD.

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses based on differential privacy, as well as heuristic defenses based on gradient compression as countermeasures. These defenses have so far been very effective, in particular those based on gradient compression that allow the model to maintain high accuracy while greatly reducing the effectiveness of attacks. In this work, we argue that such findings underestimate the privacy risk in FL. As a counterexample, we show that existing defenses can be broken by a simple adaptive attack, where a model trained on auxiliary data is able to invert gradients on both vision and language tasks.

Federated learning (FL) enables clients to collaborate with a server to train a machine learning model. To ensure privacy, the server performs secure aggregation of updates from the clients. Unfortunately, this prevents verification of the well-formedness (integrity) of the updates as the updates are masked. Consequently, malformed updates designed to poison the model can be injected without detection. In this paper, we formalize the problem of ensuring both update privacy and integrity in FL and present a new system, EIFFeL, that enables secure aggregation of verified updates. EIFFeL is a general framework that can enforce arbitrary integrity checks and remove malformed updates from the aggregate, without violating privacy. Our empirical evaluation demonstrates the practicality of EIFFeL. For instance, with 100 clients and 10% poisoning, EIFFeL can train an MNIST classification model to the same accuracy as that of a non-poisoned federated learner in just 2.4s per iteration.

Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy attacks. However, existing semantic guarantees for DP focus on membership inference, which may overestimate the adversary’s capabilities and is not applicable when membership status itself is non-sensitive. In this paper, we derive the first semantic guarantees for DP mechanisms against training data reconstruction attacks under a formal threat model. We show that two distinct privacy accounting methods—Renyi differential privacy and Fisher information leakage—both offer strong semantic protection against data reconstruction attacks.

Machine-learning models contain information about the data they were trained on. This information leaks either through the model itself or through predictions made by the model. Consequently, when the training data contains sensitive attributes, assessing the amount of information leakage is paramount. We propose a method to quantify this leakage using the Fisher information of the model about the data. Unlike the worst-case a priori guarantees of differential privacy, Fisher information loss measures leakage with respect to specific examples, attributes, or sub-populations within the dataset. We motivate Fisher information loss through the Cramer-Rao bound and delineate the implied threat model. We provide efficient methods to compute Fisher information loss for output-perturbed generalized linear models. Finally, we empirically validate Fisher information loss as a useful measure of information leakage.

Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate aggregate statistics. Two major challenges in this framework are privacy, since user data is often sensitive, and compression, since the user devices have low network bandwidth. Prior work has addressed these challenges separately by combining standard compression algorithms with known privacy mechanisms. In this work, we take a holistic look at the problem and design a family of privacy-aware compression mechanisms that work for any given communication budget. We first propose a mechanism for transmitting a single real number that has optimal variance under certain conditions. We then show how to extend it to metric differential privacy for location privacy use-cases, as well as vectors, for application to federated learning. Our experiments illustrate that our mechanism can lead to better utility vs. compression trade-offs for the same privacy loss in a number of settings.

We propose the first general-purpose gradientbased adversarial attack against transformer models.Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix, hence enabling gradient-based optimization.We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks, outperforming prior work in terms of adversarial success rate with matching imperceptibility as per automated and human evaluation.Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.

Most computer science conferences rely on paper bidding to assign reviewers to papers. Although paper bidding enables high-quality assignments in days of unprecedented submission numbers, it also opens the door for dishonest reviewers to adversarially influence paper reviewing assignments. Anecdotal evidence suggests that some reviewers bid on papers by "friends" or colluding authors, even though these papers are outside their area of expertise, and recommend them for acceptance without considering the merit of the work. In this paper, we study the efficacy of such bid manipulation attacks and find that, indeed, they can jeopardize the integrity of the review process. We develop a novel approach for paper bidding and assignment that is much more robust against such attacks. We show empirically that our approach provides robustness even when dishonest reviewers collude, have full knowledge of the assignment system’s internal workings, and have access to the system’s inputs. In addition to being more robust, the quality of our paper review assignments is comparable to that of current, non-robust assignment approaches.

Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common corruptions also introduce a large computational overhead, requiring as many as ten times the number of forward and backward passes in order to converge. To combat this inefficiency, we propose BulletTrain, a boundary example mining technique to drastically reduce the computational cost of robust training. Our key observation is that only a small fraction of examples are beneficial for improving robustness. BulletTrain dynamically predicts these important examples and optimizes robust training algorithms to focus on the important examples. We apply our technique to several existing robust training algorithms and achieve a 2.2x speed-up for TRADES and MART on CIFAR-10 and a 1.7x speed-up for AugMix on CIFAR-10-C and CIFAR-100-C without any reduction in clean and robust accuracy.

Out-of-distribution (OOD) detection has received much attention lately due to its practical importance in enhancing the safe deployment of neural networks. One of the primary challenges is that models often produce highly confident predictions on OOD data, which undermines the driving principle in OOD detection that the model should only be confident about in-distribution samples. In this work, we propose ReAct—a simple and effective technique for reducing model overconfidence on OOD data. Our method is motivated by novel analysis on internal activations of neural networks, which displays highly distinctive signature patterns for OOD distributions. Our method can generalize effectively to different network architectures and different OOD detection scores. We empirically demonstrate that ReAct achieves competitive detection performance on a comprehensive suite of benchmark datasets, and give theoretical explication for our method’s efficacy. On the ImageNet benchmark, ReAct reduces the false positive rate (FPR95) by 25.05% compared to the previous best method.

Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options, etc. Models in these systems are often developed and trained independently, which raises an obvious concern: Can improving a machine-learning model make the overall system worse? We answer this question affirmatively by showing that improving a model can deteriorate the performance of downstream models, even after those downstream models are retrained. Such self-defeating improvements are the result of entanglement between the models in the system. We perform an error decomposition of systems with multiple machine-learning models, which sheds light on the types of errors that can lead to self-defeating improvements. We also present the results of experiments which show that self-defeating improvements emerge in a realistic stereo-based detection system for cars and pedestrians.

Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually changing and the model must dynamically adapt to it without observing the true label. This setting is common in many real world scenarios such as medical diagnosis, where disease prevalences can vary substantially at different times of the year. Leveraging a novel analysis, we show that the lack of true label does not hinder estimation of the expected test loss, which enables the reduction of online label shift adaptation to conventional online learning. Informed by this observation, we propose adaptation algorithms inspired by classical online learning techniques such as Follow The Leader (FTL) and Online Gradient Descent (OGD) and derive their regret bounds. We empirically verify our findings under both simulated and real world label distribution shifts and show that OGD is particularly effective and robust to a variety of challenging label shift scenarios.

Machine-learning models contain information about the data they were trained on. This information leaks either through the model itself or through predictions made by the model. Consequently, when the training data contains sensitive attributes, assessing the amount of information leakage is paramount. We propose a method to quantify this leakage using the Fisher information of the model about the data. Unlike the worst-case a priori guarantees of differential privacy, Fisher information loss measures leakage with respect to specific examples, attributes, or sub-populations within the dataset. We motivate Fisher information loss through the Cram\’{e}r-Rao bound and delineate the implied threat model. We provide efficient methods to compute Fisher information loss for output-perturbed generalized linear models. Finally, we empirically validate Fisher information loss as a useful measure of information leakage.

Good data stewardship requires removal of data at the request of the data’s owner. This raises the question if and how a trained machine-learning model, which implicitly stores information about its training data, should be affected by such a removal request. Is it possible to “remove” data from a machine-learning model? We study this problem by defining certified removal: a very strong theoretical guarantee that a model from which data is removed cannot be distinguished from a model that never observed the data to begin with. We develop a certified-removal mechanism for linear classifiers and empirically study learning settings in which this mechanism is practical.

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumption of requiring continuous-valued confidence scores, our highly query-efficient algorithm utilizes the following simple iterative principle: we randomly sample a vector from a predefined orthonormal basis and either add or subtract it to the target image. Despite its simplicity, the proposed method can be used for both untargeted and targeted attacks – resulting in previously unprecedented query efficiency in both settings. We demonstrate the efficacy and efficiency of our algorithm on several real world settings including the Google Cloud Vision API. We argue that our proposed algorithm should serve as a strong baseline for future black-box attacks, in particular because it is extremely fast and its implementation requires less than 20 lines of PyTorch code.

In extreme classification settings, embedding-based neural network models are currently not competitive with sparse linear and tree-based methods in terms of accuracy. Most prior works attribute this poor performance to the low-dimensional bottleneck in embedding-based methods. In this paper, we demonstrate that theoretically there is no limitation to using low-dimensional embedding-based methods, and provide experimental evidence that overfitting is the root cause of the poor performance of embedding-based methods. These findings motivate us to investigate novel data augmentation and regularization techniques to mitigate overfitting. To this end, we propose GLaS, a new regularizer for embedding-based neural network approaches. It is a natural generalization from the graph Laplacian and spread-out regularizers, and empirically it addresses the drawback of each regularizer alone when applied to the extreme classification setup. With the proposed techniques, we attain or improve upon the state-of-the-art on most widely tested public extreme classification datasets with hundreds of thousands of labels.

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks have been proposed, they are easily bypassed when the adversary has full knowledge of the detection mechanism and adapts the attack strategy accordingly. In this paper, we adopt a novel perspective and regard the omnipresence of adversarial perturbations as a strength rather than a weakness. We postulate that if an image has been tampered with, these adversarial directions either become harder to find with gradient methods or have substantially higher density than for natural images. We develop a practical test for this signature characteristic to successfully detect adversarial attacks, achieving unprecedented accuracy under the white-box setting where the adversary is given full knowledge of our detection mechanism.

Bayesian optimization has proven invaluable for black-box optimization of expensive functions. Its main limitation is its exponential complexity with respect to the dimensionality of the search space using typical kernels. Luckily, many objective functions can be decomposed into additive subproblems, which can be optimized independently. We investigate how to automatically discover such (typically unknown) additive structure while simultaneously exploiting it through Bayesian optimization. We propose an efficient algorithm based on Metropolis-Hastings sampling and demonstrate its efficacy empirically on synthetic and real-world data sets. Throughout all our experiments we reliably discover hidden additive structure whenever it exists and exploit it to yield significantly faster convergence.

Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling – a single-parameter variant of Platt Scaling – is surprisingly effective at calibrating predictions.

Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning. These include web-search ranking, document recommendation, multi-lingual document matching, and article categorization. Recently, a new document metric, the word mover's distance (WMD), has been proposed with unprecedented results on kNN-based document classification. The WMD elevates high quality word embeddings to document metrics by formulating the distance between two documents as an optimal transport problem between the embedded words. However, the document distances are entirely unsupervised and lack a mechanism to incorporate supervision when available. In this paper we propose an efficient technique to learn a supervised metric, which we call the Supervised WMD (S-WMD) metric. Our algorithm learns document distances that measure the underlying semantic differences between documents by leveraging semantic differences between individual words discovered during supervised training. This is achieved with an linear transformation of the underlying word embedding space and tailored word-specific weights, learned to minimize the stochastic leave-one-out nearest neighbor classification error on a per-document level. We evaluate our metric on eight real-world text classification tasks on which S-WMD consistently outperforms almost all of our 26 competitive baselines.

A length n word is (palindromic) rich if it contains the maximum possible number, which is n , of distinct non-empty palindromic factors. We prove both necessary and sufficient conditions for richness in terms of run-length encodings of words. Relating sufficient conditions to integer partitions, we prove a lower bound of order C n , where C ≈ 37.6 , on the growth function of the language of binary rich words. From experimental study we suggest that this growth function actually grows more slowly than n n , which makes our lower bound quite reasonable.