Comparing Human and Machine Bias in Face Recognition

Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceived gender, skin type, lighting condition, etc. These audits are immensely important and successful at measuring algorithmic bias but have two major challenges: the audits (1) use facial recognition datasets which lack quality metadata, like LFW and CelebA, and (2) do not compare their observed algorithmic bias to the biases of their human alternatives. In this paper, we release improvements to the LFW and CelebA datasets which will enable future researchers to obtain measurements of algorithmic bias that are not tainted by major flaws in the dataset (e.g. identical images appearing in both the gallery and test set). We also use these new data to develop a series of challenging facial identification and verification questions that we administered to various algorithms and a large, balanced sample of human reviewers. We find that both computer models and human survey participants perform significantly better at the verification task, generally obtain lower accuracy rates on dark-skinned or female subjects for both tasks, and obtain higher accuracy rates when their demographics match that of the question. Computer models are observed to achieve a higher level of accuracy than the survey participants on both tasks and exhibit bias to similar degrees as the human survey participants.

Stochastic Training is Not Necessary for Generalization

It is widely believed that the implicit regularization of stochastic gradient descent (SGD) is fundamental to the impressive generalization behavior we observe in neural networks. In this work, we demonstrate that non-stochastic full-batch training can achieve strong performance on CIFAR-10 that is on-par with SGD, using modern architectures in settings with and without data augmentation. To this end, we utilize modified hyperparameters and show that the implicit regularization of SGD can be completely replaced with explicit regularization. This strongly suggests that theories that rely heavily on properties of stochastic sampling to explain generalization are incomplete, as strong generalization behavior is still observed in the absence of stochastic sampling. Fundamentally, deep learning can succeed without stochasticity. Our observations further indicate that the perceived difficulty of full-batch training is largely the result of its optimization properties and the disproportionate time and effort spent by the ML community tuning optimizers and hyperparameters for small-batch training.

Towards Transferable Adversarial Attacks on Vision Transformers

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. In this paper, we posit that adversarial attacks on transformers should be specially tailored for their architecture, jointly considering both patches and self-attention, in order to achieve high transferability. More specifically, we introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across different ViTs. We show that skipping the gradients of attention during backpropagation can generate adversarial examples with high transferability. In addition, adversarial perturbations generated by optimizing randomly sampled subsets of patches at each iteration achieve higher attack success rates than attacks using all patches. We evaluate the transferability of attacks on state-of-the-art ViTs, CNNs and robustly trained CNNs. The results of these experiments demonstrate that the proposed dual attack can greatly boost transferability between ViTs and from ViTs to CNNs. In addition, the proposed method can easily be combined with existing transfer methods to boost performance.

Robustness Disparities in Commercial Face Detection

Facial detection and analysis systems have been deployed by large companies and critiqued by scholars and activists for the past decade. Critiques that focus on system performance analyze disparity of the system's output, i.e., how frequently is a face detected for different Fitzpatrick skin types or perceived genders. However, we focus on the robustness of these system outputs under noisy natural perturbations. We present the first of its kind detailed benchmark of the robustness of three such systems: Amazon Rekognition, Microsoft Azure, and Google Cloud Platform. We use both standard and recently released academic facial datasets to quantitatively analyze trends in robustness for each. Across all the datasets and systems, we generally find that photos of individuals who are older, masculine presenting, of darker skin type, or have dim lighting are more susceptible to errors than their counterparts in other identities.

Datasets for Studying Generalization from Easy to Hard Examples

We describe new datasets for studying generalization from easy to hard examples.

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability

Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are responsible for erroneous decisions. We find that samples which cause similar parameters to malfunction are semantically similar. We also show that pruning the most salient parameters for a wrongly classified sample often improves model behavior. Furthermore, fine-tuning a small number of the most salient parameters on a single sample results in error correction on other samples that are misclassified for similar reasons. Based on our parameter saliency method, we also introduce an input-space saliency technique that reveals how image features cause specific network components to malfunction. Further, we rigorously validate the meaningfulness of our saliency maps on both the dataset and case-study levels.

Long-Short Transformer: Efficient Transformers for Language and Vision

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations and a short-term attention to capture fine-grained local correlations. We propose a dual normalization strategy to account for the scale mismatch between the two attention mechanisms. Transformer-LS can be applied to both autoregressive and bidirectional models without additional complexity. Our method outperforms the state-of-the-art models on multiple tasks in language and vision domains, including the Long Range Arena benchmark, autoregressive language modeling, and ImageNet classification. For instance, Transformer-LS achieves 0.97 test BPC on enwik8 using half the number of parameters than previous method, while being faster and is able to handle 3x as long sequences compared to its full-attention version on the same hardware. On ImageNet, it can obtain the state-of-the-art results (e.g., a moderate size of 55.8M model solely trained on 224x224 ImageNet-1K can obtain Top-1 accuracy 84.1%), while being more scalable on high-resolution images. The source code and models are released at https://github.com/NVIDIA/transformer-ls .

Adversarial Examples Make Strong Poisons

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. Our findings indicate that adversarial examples, when assigned the original label of their natural base image, cannot be used to train a classifier for natural images. Furthermore, when adversarial examples are assigned their adversarial class label, they are useful for training. This suggests that adversarial examples contain useful semantic content, just with the ``wrong'' labels (according to a network, but not a human). Our method, adversarial poisoning, is substantially more effective than existing poisoning methods for secure dataset release, and we release a poisoned version of ImageNet, ImageNet-P, to encourage research into the strength of this form of data obfuscation.

MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data

Class-imbalanced data, in which some classes contain far more samples than others, is ubiquitous in real-world applications. Standard techniques for handling class-imbalance usually work by training on a re-weighted loss or on re-balanced data. Unfortunately, training overparameterized neural networks on such objectives causes rapid memorization of minority class data. To avoid this trap, we harness meta-learning, which uses both an ''outer-loop'' and an ''inner-loop'' loss, each of which may be balanced using different strategies. We evaluate our method, MetaBalance, on image classification, credit-card fraud detection, loan default prediction, and facial recognition tasks with severely imbalanced data, and we find that MetaBalance outperforms a wide array of popular re-sampling strategies.

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This vulnerability is then activated at inference time by placing a "trigger" into the model's input. Typical backdoor attacks insert the trigger directly into the training data, although the presence of such an attack may be visible upon inspection. In contrast, the Hidden Trigger Backdoor Attack achieves poisoning without placing a trigger into the training data at all. However, this hidden trigger attack is ineffective at poisoning neural networks trained from scratch. We develop a new hidden trigger attack, Sleeper Agent, which employs gradient matching, data selection, and target model re-training during the crafting process. Sleeper Agent is the first hidden trigger backdoor attack to be effective against neural networks trained from scratch. We demonstrate its effectiveness on ImageNet and in black-box settings. Our implementation code can be found at https://github.com/hsouri/Sleeper-Agent.