More Like this

1. BagFlip: A Certified Defense Against Data Poisoning

   Zhang, Yuhao; Albarghouthi, Aws; D'Antoni, Loris (October 2022, OpenReview.net)

   Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but not the test inputs, while in a backdoor attack the attacker can also modify test inputs. Existing model-agnostic defense approaches either cannot handle backdoor attacks or do not provide effective certificates (i.e., a proof of a defense). We present BagFlip, a model-agnostic certified approach that can effectively defend against both trigger-less and backdoor attacks. We evaluate BagFlip on image classification and malware detection datasets. BagFlip is equal to or more effective than the state-of-the-art approaches for trigger-less attacks and more effective than the state-of-the-art approaches for backdoor attacks. 

   more » « less
2. Data Free Backdoor Attacks

   https://doi.org/10.52202/079017-0753  

   Cao, Bochuan; Chen, Jinghui; Guo, Wenbo; Hu, Chuxuan; Jia, Jinyuan; Li, Bo; Song, Dawn; Xiang, Zhen (January 2024, Neural Information Processing Systems Foundation, Inc. (NeurIPS))

   Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with some clean data or modifying the model's architecture.As a result, they are 1) not applicable when clean data is unavailable, 2) less efficient when the model is large, and 3) less stealthy due to architecture changes. In this work, we propose DFBA, a novel retraining-free and data-free backdoor attack without changing the model architecture. Technically, our proposed method modifies a few parameters of a classifier to inject a backdoor. Through theoretical analysis, we verify that our injected backdoor is provably undetectable and unremovable by various state-of-the-art defenses under mild assumptions. Our evaluation on multiple datasets further demonstrates that our injected backdoor: 1) incurs negligible classification loss, 2) achieves 100\% attack success rates, and 3) bypasses six existing state-of-the-art defenses. Moreover, our comparison with a state-of-the-art non-data-free backdoor attack shows our attack is more stealthy and effective against various defenses while achieving less classification accuracy loss.We will release our code upon paper acceptance. 

   more » « less
3. Cbd: A certified backdoor detector based on local dominant probability

   Xiang, Zhen; Xiong, Zidi; Li, Bo (December 2023, Advances in Neural Information Processing Systems)

   Backdoor attack is a common threat to deep neural networks. During testing, samples embedded with a backdoor trigger will be misclassified as an adversarial target by a backdoored model, while samples without the backdoor trigger will be correctly classified. In this paper, we present the first certified backdoor detector (CBD), which is based on a novel, adjustable conformal prediction scheme based on our proposed statistic local dominant probability. For any classifier under inspection, CBD provides 1) a detection inference, 2) the condition under which the attacks are guaranteed to be detectable for the same classification domain, and 3) a probabilistic upper bound for the false positive rate. Our theoretical results show that attacks with triggers that are more resilient to test-time noise and have smaller perturbation magnitudes are more likely to be detected with guarantees. Moreover, we conduct extensive experiments on four benchmark datasets considering various backdoor types, such as BadNet, CB, and Blend. CBD achieves comparable or even higher detection accuracy than state-of-the-art detectors, and it in addition provides detection certification. Notably, for backdoor attacks with random perturbation triggers bounded by which achieves more than 90\% attack success rate, CBD achieves 100\%(98\%), 100\%(84\%), 98\%(98\%), and 72\%(40\%) empirical (certified) detection true positive rates on the four benchmark datasets GTSRB, SVHN, CIFAR-10, and TinyImageNet, respectively, with low false positive rates. 

   more » « less
4. Excess Capacity and Backdoor Poisoning

   Manoj, Naren; Blum, Avrim (January 2021, Advances in neural information processing systems)

   A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical data; however, the model reliably errs on watermarked examples. To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. We then use this to analyze important statistical and computational issues surrounding these attacks. On the statistical front, we identify a parameter we call the memorization capacity that captures the intrinsic vulnerability of a learning problem to a backdoor attack. This allows us to argue about the robustness of several natural learning problems to backdoor attacks. Our results favoring the attacker involve presenting explicit constructions of backdoor attacks, and our robustness results show that some natural problem settings cannot yield successful backdoor attacks. From a computational standpoint, we show that under certain assumptions, adversarial training can detect the presence of backdoors in a training set. We then show that under similar assumptions, two closely related problems we call backdoor filtering and robust generalization are nearly equivalent. This implies that it is both asymptotically necessary and sufficient to design algorithms that can identify watermarked examples in the training set in order to obtain a learning algorithm that both generalizes well to unseen data and is robust to backdoors. 

   more » « less
5. Sub-Band Backdoor Attack in Remote Sensing Imagery

   https://doi.org/10.3390/a17050182  

   Islam, Kazi Aminul (May 2024, Algorithms)

   Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in the data. Backdoor attacks have been extensively studied in machine learning-based computer vision applications with natural images. However, much less research has been conducted on remote sensing imagery, which typically consists of many more bands in addition to the red, green, and blue bands found in natural images. In this paper, we first extensively studied a popular backdoor attack, BadNets, applied to a remote sensing dataset, where the trigger was planted in all of the bands in the data. Our results showed that SOTA defense mechanisms, including Neural Cleanse, TABOR, Activation Clustering, Fine-Pruning, GangSweep, Strip, DeepInspect, and Pixel Backdoor, had difficulties detecting and mitigating the backdoor attack. We then proposed an explainable AI-guided backdoor attack specifically for remote sensing imagery by placing triggers in the image sub-bands. Our proposed attack model even poses stronger challenges to these SOTA defense mechanisms, and no method was able to defend it. These results send an alarming message about the catastrophic effects the backdoor attacks may have on satellite imagery. 

   more » « less