ICML 2024 Papers

Offline Reinforcement Learning (RL) commonly suffers from the out-of-distribution (OOD) overestimation issue due to the distribution shift. Prior work gradually shifts their focus from suppressing OOD overestimation to avoiding overly conservative learning from suboptimal behavior policies to improve generalization. However, most approaches explicitly delimit boundaries for OOD actions based on the support in the dataset, which can potentially impede the data near these boundaries from acquiring realistic estimates. This paper investigates how to loosen the rigid demarcation of OOD boundaries, adaptively extracting knowledge from empirical data to implicitly improve the model's generalization to nearby unseen data. We introduce an adversarial data splitting (ADS) framework that enforces the model to generalize the distribution shifts simulated from the train/validation subsets splitting of the dataset. Specifically, ADS is modeled as a min-max optimization problem inspired by meta-learning and solved by iterating over the following two steps. First, we train the model on the train-subset to minimize its loss on the validation-subset. Then, we adversarially generate the "hardest" train/validation subsets with the maximum distribution shift, making the model incapable of generalization at that splitting. We derive a generalization error bound for theoretically understanding ADS and verify the effectiveness with extensive experiments. Code is available at https://github.com/DkING-lv6/ADS.

This paper studies the challenging black-box adversarial attack that aims to generate adversarial examples against a black-box model by only using output feedback of the model to input queries. Some previous methods improve the query efficiency by incorporating the gradient of a surrogate white-box model into query-based attacks due to the adversarial transferability. However, the localized gradient is not informative enough, making these methods still query-intensive. In this paper, we propose a Prior-guided Bayesian Optimization (P-BO) algorithm that leverages the surrogate model as a global function prior in black-box adversarial attacks. As the surrogate model contains rich prior information of the black-box one, P-BO models the attack objective with a Gaussian process whose mean function is initialized as the surrogate model's loss. Our theoretical analysis on the regret bound indicates that the performance of P-BO may be affected by a bad prior. Therefore, we further propose an adaptive integration strategy to automatically adjust a coefficient on the function prior by minimizing the regret bound. Extensive experiments on image classifiers and large vision-language models demonstrate the superiority of the proposed algorithm in reducing queries and improving attack success rates compared with the state-of-the-art black-box attacks. Code is available at https://github.com/yibo-miao/PBO-Attack.

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adversarial examples. While character-level attacks easily maintain semantics, they have received less attention as they cannot easily adopt popular gradient-based methods, and are thought to be easy to defend. Challenging these beliefs, we introduce Charmer, an efficient query-based adversarial attack capable of achieving high attack success rate (ASR) while generating highly similar adversarial examples. Our method successfully targets both small (BERT) and large (Llama 2) models. Specifically, on BERT with SST-2, Charmer improves the ASR in $4.84$% points and the USE similarity in $8$% points with respect to the previous art. Our implementation is available in https://github.com/LIONS-EPFL/Charmer.

Research on adversarial robustness has predominantly focused on continuous inputs, leaving categorical inputs, especially tabular attributes, less examined. To echo this challenge, our work aims to evaluate and enhance the robustness of classification over categorical attributes against adversarial perturbations through efficient attack-free approaches. We propose a robustness evaluation metric named Integrated Gradient-Smoothed Gradient (IGSG). It is designed to evaluate the attributional sensitivity of each feature and the decision boundary of the classifier, two aspects that significantly influence adversarial risk, according to our theoretical analysis. Leveraging this metric, we develop an IGSG-based regularization to reduce adversarial risk by suppressing the sensitivity of categorical attributes. We conduct extensive empirical studies over categorical datasets of various application domains. The results affirm the efficacy of both IGSG and IGSG-based regularization. Notably, IGSG-based regularization surpasses the state-of-the-art robust training methods by a margin of approximately 0.4% to 12.2% on average in terms of adversarial accuracy, especially on high-dimension datasets. The code is available at https://github.com/YujunZhou/IGSG.

Many existing anomaly detection methods assume the availability of a large-scale normal dataset. But for many applications, limited by resources, removing all anomalous samples from a large un-labeled dataset is unrealistic, resulting in contaminated datasets. To detect anomalies accurately under such scenarios, from the probabilistic perspective, the key question becomes how to learn the normal-data distribution from a contaminated dataset. To this end, we propose to collect two additional small datasets that are comprised of partially-observed normal and anomaly samples, and then use them to help learn the distribution under an adversarial learning scheme. We prove that under some mild conditions, the proposed method is able to learn the correct normal-data distribution. Then, we consider the overfitting issue caused by the small size of the two additional datasets, and a correctness-guaranteed flipping mechanism is further developed to alleviate it. Theoretical results under incomplete observed anomaly types are also presented. Extensive experimental results demonstrate that our method outperforms representative baselines when detecting anomalies under contaminated datasets.

Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstable results, putting their overall reliability into question. In this work, we aim to systematically improve the quality of feature attributions by combining multiple explanations across distinct methods or their variations. For this purpose, we propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria such as robustness or faithfulness to the model behavior. Through extensive experiments involving various model architectures and popular feature attribution techniques, we demonstrate that our combination strategy consistently outperforms individual methods and existing baselines.

In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used $l_{\infty}$-norm bounded attack if the model is not adversarially trained, which underpins the importance of adversarial training for CP. Our paper next demonstrates that the prediction set size (PSS) of CP using adversarially trained models with AT variants is often worse than using standard AT, inspiring us to research into CP-efficient AT for improved PSS. We propose to optimize a Beta-weighting loss with an entropy minimization regularizer during AT to improve CP-efficiency, where the Beta-weighting loss is shown to be an upper bound of PSS at the population level by our theoretical analysis. Moreover, our empirical study on four image classification datasets across three popular AT baselines validates the effectiveness of the proposed Uncertainty-Reducing AT (AT-UR).

This work studies sparse adversarial perturbations bounded by $l_0$ norm. We propose a white-box PGD-like attack method named sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against $l_0$ bounded adversarial perturbations. Moreover, the efficiency of sparse-PGD enables us to conduct adversarial training to build robust models against sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks. Codes are available at https://github.com/CityU-MLO/sPGD.

In adversarial defense, adversarial purification can be viewed as a special generation task with the purpose to remove adversarial attacks and diffusion models excel in adversarial purification for their strong generative power. With different predetermined generation requirements, various types of guidance have been proposed, but few of them focuses on adversarial purification. In this work, we propose to guide diffusion models for adversarial purification using contrastive guidance. We theoretically derive the proper noise level added in the forward process diffusion models for adversarial purification from a feature learning perspective. For the reverse process, it is implied that the role of contrastive loss guidance is to facilitate the evolution towards the signal direction. From the theoretical findings and implications, we design the forward process with the proper amount of Gaussian noise added and the reverse process with the gradient of contrastive loss as the guidance of diffusion models for adversarial purification. Empirically, extensive experiments on CIFAR-10, CIFAR-100, the German Traffic Sign Recognition Benchmark and ImageNet datasets with ResNet and WideResNet classifiers show that our method outperforms most of current adversarial training and adversarial purification methods by a large improvement.

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from inevitably decreased clean accuracy. Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization. However, as SAM is designed for better clean accuracy, its effectiveness in enhancing adversarial robustness remains unexplored. In this work, considering the duality between SAM and AT, we investigate the adversarial robustness derived from SAM. Intriguingly, we find that using SAM alone can improve adversarial robustness. To understand this unexpected property of SAM, we first provide empirical and theoretical insights into how SAM can implicitly learn more robust features, and conduct comprehensive experiments to show that SAM can improve adversarial robustness notably without sacrificing any clean accuracy, shedding light on the potential of SAM to be a substitute for AT when accuracy comes at a higher priority. Code is available at https://github.com/weizeming/SAM_AT.

We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capture the vulnerability and robustness of CMAB. The attackability condition depends on the intrinsic properties of the corresponding CMAB instance such as the reward distributions of super arms and outcome distributions of base arms. Additionally, we devise an attack algorithm for attackable CMAB instances. Contrary to prior understanding of multi-armed bandits, our work reveals a surprising fact that the attackability of a specific CMAB instance also depends on whether the bandit instance is known or unknown to the adversary. This finding indicates that adversarial attacks on CMAB are difficult in practice and a general attack strategy for any CMAB instance does not exist since the environment is mostly unknown to the adversary. We validate our theoretical findings via extensive experiments on real-world CMAB applications including probabilistic maximum covering problem, online minimum spanning tree, cascading bandits for online ranking, and online shortest path.

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (D-VAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://github.com/yuyi-sd/D-VAE.