论文检索

Social Aspects · Trustworthy Machine Learning

Shaopeng Fu, Di Wang

Adversarial training (AT) is a canonical method for enhancing the robustness of deep neural networks (DNNs). However, recent studies empirically demonstrated that it suffers from robust overfitting, i.e., a long time AT can be detrimental to the robustness of DNNs. This paper presents a theoretical explanation of robust overfitting for DNNs. Specifically, we non-trivially extend the neural tangent kernel (NTK) theory to AT and prove that an adversarially trained wide DNN can be well approximated by a linearized DNN. Moreover, for squared loss, closed-form AT dynamics for the linearized DNN can be derived, which reveals a new AT degeneration phenomenon: a long-term AT will result in a wide DNN degenerates to that obtained without AT and thus cause robust overfitting. Based on our theoretical results, we further design a method namely Adv-NTK, the first AT algorithm for infinite-width DNNs. Experiments on real-world datasets show that Adv-NTK can help infinite-width DNNs enhance comparable robustness to that of their finite-width counterparts, which in turn justifies our theoretical findings. The code is available at https://github.com/fshp971/adv-ntk.

Social Aspects · Trustworthy Machine Learning

Bo Peng, Yadan Luo, Yonggang Zhang, Yixuan Li, Zhen Fang

Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribution assumptions to identify low-scoring OOD samples. Nevertheless, these estimate scores may fail to accurately reflect the true data density or impose impractical constraints. To provide a unified perspective on density-based score design, we propose a novel theoretical framework grounded in Bregman divergence, which extends distribution considerations to encompass an exponential family of distributions. Leveraging the conjugation constraint revealed in our theorem, we introduce a \textsc{ConjNorm} method, reframing density function design as a search for the optimal norm coefficient $p$ against the given dataset. In light of the computational challenges of normalization, we devise an unbiased and analytically tractable estimator of the partition function using the Monte Carlo-based importance sampling technique. Extensive experiments across OOD detection benchmarks empirically demonstrate that our proposed \textsc{ConjNorm} has established a new state-of-the-art in a variety of OOD detection setups, outperforming the current best method by up to 13.25\% and 28.19\% (FPR95) on CIFAR-100 and ImageNet-1K, respectively.

Social Aspects · Accountability, Transparency and Interpretability

Aliyah Hsu, Yeshwanth Cherapanamjeri, Briton Park, Tristan Naumann, Anobel Odisho, Bin Yu

Pre-trained transformers are often fine-tuned to aid clinical decision-making using limited clinical notes. Model interpretability is crucial, especially in high-stakes domains like medicine, to establish trust and ensure safety, which requires human engagement. We introduce SUFO, a systematic framework that enhances interpretability of fine-tuned transformer feature spaces. SUFO utilizes a range of analytic and visualization techniques, including Supervised probing, Unsupervised similarity analysis, Feature dynamics, and Outlier analysis to address key questions about model trust and interpretability (e.g. model suitability for a task, feature space evolution during fine-tuning, and interpretation of fine-tuned features and failure modes). We conduct a case study investigating the impact of pre-training data where we focus on real-world pathology classification tasks, and validate our findings on MedNLI. We evaluate five 110M-sized pre-trained transformer models, categorized into general-domain (BERT, TNLR), mixed-domain (BioBERT, Clinical BioBERT), and domain-specific (PubMedBERT) groups. Our SUFO analyses reveal that: (1) while PubMedBERT, the domain-specific model, contains valuable information for fine-tuning, it can overfit to minority classes when class imbalances exist. In contrast, mixed-domain models exhibit greater resistance to overfitting, suggesting potential improvements in domain-specific model robustness; (2) in-domain pre-training accelerates feature disambiguation during fine-tuning; and (3) feature spaces undergo significant sparsification during this process, enabling clinicians to identify common outlier modes among fine-tuned models as demonstrated in this paper. These findings showcase the utility of SUFO in enhancing trust and safety when using transformers in medicine, and we believe SUFO can aid practitioners in evaluating fine-tuned language models (LMs) for other applications in medicine and in more critical domains.

Social Aspects · Fairness, Equity, Justice and Safety

Tongxin Yin, Jean-Francois Ton, Ruocheng Guo, Yuanshun Yao, Mingyan Liu, Yang Liu

In critical applications, it is vital for classifiers to defer decision-making to humans. We propose a post-hoc method that makes existing classifiers selectively abstain from predicting certain samples. Our abstaining classifier is incentivized to maintain the original accuracy for each sub-population (i.e. no harm) while achieving a set of group fairness definitions to a user specified degree. To this end, we design an Integer Programming (IP) procedure that assigns abstention decisions for each training sample to satisfy a set of constraints. To generalize the abstaining decisions to test samples, we then train a surrogate model to learn the abstaining decisions based on the IP solutions in an end-to-end manner. We analyze the feasibility of the IP procedure to determine the possible abstention rate for different levels of unfairness tolerance and accuracy constraint for achieving no harm. To the best of our knowledge, this work is the first to identify the theoretical relationships between the constraint parameters and the required abstention rate. Our theoretical results are important since a high abstention rate is often infeasible in practice due to a lack of human resources. Our framework outperforms existing methods in terms of fairness disparity without sacrificing accuracy at similar abstention rates.

Social Aspects · Trustworthy Machine Learning

Anastasios Angelopoulos, Stephen Bates, Adam Fisch, Lihua Lei, Tal Schuster

We extend conformal prediction to control the expected value of any monotone loss function. The algorithm generalizes split conformal prediction together with its coverage guarantee. Like conformal prediction, the conformal risk control procedure is tight up to an $\mathcal{O}(1/n)$ factor. We also introduce extensions of the idea to distribution shift, quantile risk control, multiple and adversarial risk control, and expectations of U-statistics. Worked examples from computer vision and natural language processing demonstrate the usage of our algorithm to bound the false negative rate, graph distance, and token-level F1-score.

Social Aspects · Trustworthy Machine Learning

Zhiyuan Cheng, Hongjun Choi, Shiwei Feng, James Liang, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang

Multi-sensor fusion (MSF) is widely used in autonomous vehicles (AVs) for perception, particularly for 3D object detection with camera and LiDAR sensors. The purpose of fusion is to capitalize on the advantages of each modality while minimizing its weaknesses. Advanced deep neural network (DNN)-based fusion techniques have demonstrated the exceptional and industry-leading performance. Due to the redundant information in multiple modalities, MSF is also recognized as a general defence strategy against adversarial attacks. In this paper, we attack fusion models from the camera modality that is considered to be of lesser importance in fusion but is more affordable for attackers. We argue that the weakest link of fusion models depends on their most vulnerable modality and propose an attack framework that targets advanced camera-LiDAR fusion-based 3D object detection models through camera-only adversarial attacks. Our approach employs a two-stage optimization-based strategy that first thoroughly evaluates vulnerable image areas under adversarial attacks, and then applies dedicated attack strategies for different fusion models to generate deployable patches. The evaluations with six advanced camera-LiDAR fusion models and one camera-only model indicate that our attacks successfully compromise all of them. Our approach can either decrease the mean average precision (mAP) of detection performance from 0.824 to 0.353 or degrade the detection score of a target object from 0.728 to 0.156, demonstrating the efficacy of our proposed attack framework. Code is available.

Social Aspects · Trustworthy Machine Learning

Shuhai Zhang, Yiliao Song, Jiahao Yang, Yuanqing Li, Bo Han, Mingkui Tan

Large language models (LLMs) such as ChatGPT have exhibited remarkable performance in generating human-like texts. However, machine-generated texts (MGTs) may carry critical risks, such as plagiarism issues and hallucination information. Therefore, it is very urgent and important to detect MGTs in many situations. Unfortunately, it is challenging to distinguish MGTs and human-written texts because the distributional discrepancy between them is often very subtle due to the remarkable performance of LLMS. In this paper, we seek to exploit \textit{maximum mean discrepancy} (MMD) to address this issue in the sense that MMD can well identify distributional discrepancies. However, directly training a detector with MMD using diverse MGTs will incur a significantly increased variance of MMD since MGTs may contain \textit{multiple text populations} due to various LLMs. This will severely impair MMD's ability to measure the difference between two samples. To tackle this, we propose a novel \textit{multi-population} aware optimization method for MMD called MMD-MP, which can \textit{avoid variance increases} and thus improve the stability to measure the distributional discrepancy. Relying on MMD-MP, we develop two methods for paragraph-based and sentence-based detection, respectively. Extensive experiments on various LLMs, \eg, GPT2 and ChatGPT, show superior detection performance of our MMD-MP.

Social Aspects · Trustworthy Machine Learning

Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan Ullman

The integration of Machine Learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for ML training purposes. One such privacy risk is Membership Inference (MI), in which an adversary seeks to determine whether a particular data point was included in the training dataset of a model. Current state-of-the-art MI approaches capitalize on access to the model’s predicted confidence scores to successfully perform membership inference, and employ data poisoning to further enhance their effectiveness. In this work, we focus on the less explored and more realistic label-only setting, where the model provides only the predicted label as output. We show that existing label-only attacks are ineffective at inferring membership in the low False Positive Rate (FPR) regime. To address this challenge, we propose a new attack Chameleon that leverages a novel data poisoning strategy and an efficient query selection method to achieve significantly more accurate membership inference than existing label-only attacks, especially for low FPRs.

Social Aspects · Privacy-preserving Statistics and Machine Learning

Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang

Label differentially private (label DP) algorithms seek to preserve the privacy of the labels in a training dataset in settings where the features are known to the adversary. In this work, we study a new family of label DP training algorithms. Unlike most prior label DP algorithms that have been based on label randomization, our algorithm naturally leverages the power of the central model of DP. It interleaves gradient projection operations with private stochastic gradient descent steps in order to improve the utility of the trained model while guaranteeing the privacy of the labels. We show that such projection-based algorithms can be made practical and that they improve on the state-of-the art for label DP training in the high-privacy regime. We complement our empirical evaluation with theoretical results shedding light on the efficacy of our method through the lens of bias-variance trade-offs.

Social Aspects · Fairness, Equity, Justice and Safety

Maarten Buyl, MaryBeth Defrance, Tijl De Bie

Current tools for machine learning fairness only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines.We introduce a framework of fairness regularization terms (fairret) which quantify bias as modular objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.

Social Aspects · Everything Else

Mingzhen Huang, Shan Jia, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu

In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning. Existing classification-based methods for text-image inconsistency can identify contextual inconsistencies but fail to provide explainable justifications for their decisions that humans can understand. Although more nuanced, human evaluation is impractical at scale and susceptible to errors. To address these limitations, this study introduces D-TIIL (Diffusion-based Text-Image Inconsistency Localization), which employs text-to-image diffusion models to localize semantic inconsistencies in text and image pairs. These models, trained on large-scale datasets act as ``omniscient" agents that filter out irrelevant information and incorporate background knowledge to identify inconsistencies. In addition, D-TIIL uses text embeddings and modified image regions to visualize these inconsistencies. To evaluate D-TIIL's efficacy, we introduce a new TIIL dataset containing 14K consistent and inconsistent text-image pairs. Unlike existing datasets, TIIL enables assessment at the level of individual words and image regions and is carefully designed to represent various inconsistencies. D-TIIL offers a scalable and evidence-based approach to identifying and localizing text-image inconsistency, providing a robust framework for future research combating misinformation.

Social Aspects · Accountability, Transparency and Interpretability

Nils Lukas, Abdelrahman Ahmed, Lucas Fenaux, Florian Kerschbaum

Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret watermarking key. A core security property of watermarking is robustness, which states that an attacker can only evade detection by substantially degrading image quality. Assessing robustness requires designing an adaptive attack for the specific watermarking algorithm. When evaluating watermarking algorithms and their (adaptive) attacks, it is challenging to determine whether an adaptive attack is optimal, i.e., the best possible attack. We solve this problem by defining an objective function and then approach adaptive attacks as an optimization problem. The core idea of our adaptive attacks is to replicate secret watermarking keys locally by creating surrogate keys that are differentiable and can be used to optimize the attack's parameters. We demonstrate for Stable Diffusion models that such an attacker can break all five surveyed watermarking methods at no visible degradation in image quality. Optimizing our attacks is efficient and requires less than 1 GPU hour to reduce the detection accuracy to 6.3% or less. Our findings emphasize the need for more rigorous robustness testing against adaptive, learnable attackers.

Social Aspects

Young-Jae Park, Minseok Seo, Doyi Kim, Hyeri Kim, Sanghoon Choi, Beomkyu Choi, Jeongwon Ryu, Sohee Son, Hae-Gon Jeon, Yeji Choi

In the face of escalating climate changes, typhoon intensities and their ensuing damage have surged. Accurate trajectory prediction is crucial for effective damage control. Traditional physics-based models, while comprehensive, are computationally intensive and rely heavily on the expertise of forecasters. Contemporary data-driven methods often rely on reanalysis data, which can be considered to be the closest to the true representation of weather conditions. However, reanalysis data is not produced in real-time and requires time for adjustment since prediction models are calibrated with observational data. This reanalysis data, such as ERA5, falls short in challenging real-world situations. Optimal preparedness necessitates predictions at least 72 hours in advance, beyond the capabilities of standard physics models. In response to these constraints, we present an approach that harnesses real-time Unified Model (UM) data, sidestepping the limitations of reanalysis data. Our model provides predictions at 6-hour intervals for up to 72 hours in advance and outperforms both state-of-the-art data-driven methods and numerical weather prediction models. In line with our efforts to mitigate adversities inflicted by \rthree{typhoons}, we release our preprocessed \textit{PHYSICS TRACK} dataset, which includes ERA5 reanalysis data, typhoon best-track, and UM forecast data.

Social Aspects · Trustworthy Machine Learning

Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger, Dan Jurafsky, Tatsunori Hashimoto, James Y Zou

Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily generate harmful content.In this paper, we raise concerns over the safety of models that only emphasize helpfulness, not harmlessness, in their instruction-tuning.We show that several popular instruction-tuned models are highly unsafe. Moreover, we show that adding just 3\% safety examples (a few hundred demonstrations) when fine-tuning a model like LLaMA can substantially improve its safety. Our safety-tuning does not make models significantly less capable or helpful as measured by standard benchmarks. However, we do find exaggerated safety behaviours, where too much safety-tuning makes models refuse perfectly safe prompts if they superficially resemble unsafe ones. As a whole, our results illustrate trade-offs in training LLMs to be helpful and training them to be safe.

Social Aspects · Trustworthy Machine Learning

Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models.Existing works address this problem by first identifying clusters (or directions) of incorrectly classified samples in a latent space and then aiming to provide human-understandable text descriptions for them.We observe that in some cases, describing text does not match wellwith identified failure modes, partially owing to the fact that shared interpretable attributes of failure modes may not be captured using clustering in the feature space.To improve on these shortcomings, we propose a novel approach that prioritizes interpretability in this problem: we start by obtaining human-understandable concepts (tags) of images in the dataset andthen analyze the model's behavior based on the presence or absence of combinations of these tags.Our method also ensures that the tags describing a failure mode form a minimal set,avoiding redundant and noisy descriptions.Through several experiments on different datasets, we show that our method successfully identifies failure modes and generates high-quality text descriptions associated with them.These results highlight the importance of prioritizing interpretability in understanding model failures.

Social Aspects · Fairness, Equity, Justice and Safety

Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, sylvain lamprier, Marcin Detyniecki

In the field of algorithmic fairness, significant attention has been put on group fairness criteria, such as Demographic Parity and Equalized Odds. Nevertheless, these objectives, measured as global averages, have raised concerns about persistent local disparities between sensitive groups. In this work, we address the problem of local fairness, which ensures that the predictor is unbiased not only in terms of expectations over the whole population, but also within any subregion of the feature space, unknown at training time. To enforce this objective, we introduce ROAD, a novel approach that leverages the Distributionally Robust Optimization (DRO) framework within a fair adversarial learning objective, where an adversary tries to infer the sensitive attribute from the predictions. Using an instance-level re-weighting strategy, ROAD is designed to prioritize inputs that are likely to be locally unfair, i.e. where the adversary faces the least difficulty in reconstructing the sensitive attribute. Numerical experiments demonstrate the effectiveness of our method: it achieves Pareto dominance with respect to local fairness and accuracy for a given global fairness level across three standard datasets, and also enhances fairness generalization under distribution shift.

Social Aspects · Fairness, Equity, Justice and Safety

Shaofei Shen, Chenhao Zhang, Yawen Zhao, Alina Bialkowski, Weitong Chen, Miao Xu

Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have emerged. However, these methods typically rely on complete supervision throughout the unlearning process. Unfortunately, obtaining such supervision, whether for the forgetting or remaining data, can be impractical due to the substantial cost associated with annotating real-world datasets. This challenge prompts us to propose a supervision-free unlearning approach that operates without the need for labels during the unlearning process. Specifically, we introduce a variational approach to approximate the distribution of representations for the remaining data. Leveraging this approximation, we adapt the original model to eliminate information from the forgotten data at the representation level. To further address the issue of lacking supervision information, which hinders alignment with ground truth, we introduce a contrastive loss to facilitate the matching of representations between the remaining data and those of the original model, thus preserving predictive performance. Experimental results across various unlearning tasks demonstrate the effectiveness of our proposed method, Label-Agnostic Forgetting (LAF) without using any labels, which achieves comparable performance to state-of-the-art methods that rely on full supervision information. Furthermore, our approach excels in semi-supervised scenarios, leveraging limited supervision information to outperform fully supervised baselines. This work not only showcases the viability of supervision-free unlearning in deep models but also opens up a new possibility for future research in unlearning at the representation level.

Social Aspects · Trustworthy Machine Learning

Yan Liu, Yu Liu, Xiaokang Chen, Pin-Yu Chen, Daoguang Zan, Min-Yen Kan, Tsung-Yi Ho

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused on using black-box methods such as probing to detect and quantify social biases in PLMs by observing model outputs. As a result, previous debiasing methods mainly finetune or even pre-train PLMs on newly constructed anti-stereotypical datasets, which are high-cost. In this work, we try to unveil the mystery of social bias inside language models by introducing the concept of {\sc Social Bias Neurons}. Specifically, we propose {\sc Integrated Gap Gradients (IG$^2$)} to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. By formalizing undesirable behavior as a distributional property of language, we employ sentiment-bearing prompts to elicit classes of sensitive words (demographics) correlated with such sentiments. Our IG$^2$ thus attributes the uneven distribution for different demographics to specific Social Bias Neurons, which track the trail of unwanted behavior inside PLM units to achieve interoperability. Moreover, derived from our interpretable technique, {\sc Bias Neuron Suppression (BNS)} is further proposed to mitigate social biases. By studying BERT, RoBERTa, and their attributable differences from debiased FairBERTa, IG$^2$ allows us to locate and suppress identified neurons, and further mitigate undesired behaviors. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost\footnote{This work contains examples that potentially implicate stereotypes, associations, and other harms that could be offensive to individuals in certain social groups.}.

Social Aspects · Trustworthy Machine Learning

Elias Abad Rocamora, Fanghui Liu, Grigorios Chrysos, Pablo M. Olmos, Volkan Cevher

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to $0$%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly with respect to the input, this is however lost in single-step AT. To address CO in single-step AT, several methods have been proposed to enforce local linearity of the loss via regularization. However, these regularization terms considerably slow down training due to *Double Backpropagation*. Instead, in this work, we introduce a regularization term, called ELLE, to mitigate CO *effectively* and *efficiently* in classical AT evaluations, as well as some more difficult regimes, e.g., large adversarial perturbations and long training schedules. Our regularization term can be theoretically linked to curvature of the loss function and is computationally cheaper than previous methods by avoiding *Double Backpropagation*. Our thorough experimental validation demonstrates that our work does not suffer from CO, even in challenging settings where previous works suffer from it. We also notice that adapting our regularization parameter during training (ELLE-A) greatly improves the performance, specially in large $\epsilon$ setups. Our implementation is available in https://github.com/LIONS-EPFL/ELLE.

Social Aspects · Fairness, Equity, Justice and Safety

Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In this work, we frame fairness as a distributional alignment problem. Our solution consists of two main technical contributions: (1) a distributional alignment loss that steers specific characteristics of the generated images towards a user-defined target distribution, and (2) adjusted direct finetuning of diffusion model's sampling process (adjusted DFT), which leverages an adjusted gradient to directly optimize losses defined on the generated images. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Gender bias is significantly reduced even when finetuning just five soft tokens. Crucially, our method supports diverse perspectives of fairness beyond absolute equality, which is demonstrated by controlling age to a 75% young and 25% old distribution while simultaneously debiasing gender and race. Finally, our method is scalable: it can debias multiple concepts at once by simply including these prompts in the finetuning data. We share code and various fair diffusion model adaptors at https://sail-sg.github.io/finetune-fair-diffusion/.