Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning and Certification under Instance-targeted Poisoning
263
0
0.0
(
0
)
Added by
Ji Gao
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the learner at the test instance. Our first contribution is to formalize the problem in various settings and to explicitly model subtle aspects such as the proper or improper nature of the learning, learners randomness, and whether (or not) adversarys attack can depend on it. Our main result shows that when the budget of the adversary scales sublinearly with the sample complexity, (improper) PAC learnability and certification are achievable; in contrast, when the adversarys budget grows linearly with the sample complexity, the adversary can potentially drive up the expected 0-1 loss to one. We also study distribution-specific PAC learning in the same attack model and show that proper learning with certification is possible for learning half spaces under natural distributions. Finally, we empirically study the robustness of K nearest neighbour, logistic regression, multi-layer perceptron, and convolutional neural network on real data sets against targeted-poisoning attacks. Our experimental results show that many models, especially state-of-the-art neural networks, are indeed vulnerable to these strong attacks. Interestingly, we observe that methods with high standard accuracy might be more vulnerable to instance-targeted poisoning attacks.
rate research
Read More
Certifiers for neural networks have made great progress towards provable robustness guarantees against evasion attacks using adversarial examples. However, introducing certifiers into deep learning systems also opens up new attack vectors, which need to be considered before deployment. In this work, we conduct the first systematic analysis of training time attacks against certifiers in practical application pipelines, identifying new threat vectors that can be exploited to degrade the overall system. Using these insights, we design two backdoor attacks against network certifiers, which can drastically reduce certified robustness when the backdoor is activated. For example, adding 1% poisoned data points during training is sufficient to reduce certified robustness by up to 95 percentage points, effectively rendering the certifier useless. We analyze how such novel attacks can compromise the overall systems integrity or availability. Our extensive experiments across multiple datasets, model architectures, and certifiers demonstrate the wide applicability of these attacks. A first investigation into potential defenses shows that current approaches only partially mitigate the issue, highlighting the need for new, more specific solutions.
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use clean-labels; they dont require the attacker to have any control over the labeling of training data. They are also targeted; they control the behavior of the classifier on a $textit{specific}$ test instance without degrading overall classifier performance. For example, an attacker could add a seemingly innocuous image (that is properly labeled) to a training set for a face recognition engine, and control the identity of a chosen person at test time. Because the attacker does not need to control the labeling function, poisons could be entered into the training set simply by leaving them on the web and waiting for them to be scraped by a data collection bot. We present an optimization-based method for crafting poisons, and show that just one single poison image can control classifier behavior when transfer learning is used. For full end-to-end training, we present a watermarking strategy that makes poisoning reliable using multiple ($approx$50) poisoned training instances. We demonstrate our method by generating poisoned frog images from the CIFAR dataset and using them to manipulate image classifiers.
In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks against convex machine learning models and propose an efficient poisoning attack designed to induce a specified model. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to {it any} attainable target classifier. The distance from the induced classifier to the target classifier is inversely proportional to the square root of the number of poisoning points. We also provide a lower bound on the minimum number of poisoning points needed to achieve a given target classifier. Our method uses online convex optimization, so finds poisoning points incrementally. This provides more flexibility than previous attacks which require a priori assumption about the number of poisoning points. Our attack is the first model-targeted poisoning attack that provides provable convergence for convex models, and in our experiments, it either exceeds or matches state-of-the-art attacks in terms of attack success rate and distance to the target model.
Backdoor attacks inject poisoning samples during training, with the goal of enforcing a machine-learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated in a variety of settings and against different models, the factors affecting their success are not yet well understood. In this work, we provide a unifying framework to study the process of backdoor learning under the lens of incremental learning and influence functions. We show that the success of backdoor attacks inherently depends on (i) the complexity of the learning algorithm, controlled by its hyperparameters, and (ii) the fraction of backdoor samples injected into the training set. These factors affect how fast a machine-learning model learns to correlate the presence of a backdoor trigger with the target class. Interestingly, our analysis shows that there exists a region in the hyperparameter space in which the accuracy on clean test samples is still high while backdoor attacks become ineffective, thereby suggesting novel criteria to improve existing defenses.
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.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
