Related papers: Availability Attacks Create Shortcuts
Poisoning attacks have emerged as a significant security threat to machine learning algorithms. It has been demonstrated that adversaries who make small changes to the training set, such as adding specially crafted data points, can hurt the…
Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…
Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…
Deep visual models are susceptible to adversarial perturbations to inputs. Although these signals are carefully crafted, they still appear noise-like patterns to humans. This observation has led to the argument that deep visual…
Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…
Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph learning tasks. However, recent studies show that GNNs are vulnerable to both test-time evasion and training-time poisoning attacks that perturb the graph…
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…
Dynamic networks are a complex subject. Not only do they inherit the complexity of static networks (as a particular case); they are also sensitive to definitional subtleties that are a frequent source of confusion and incomparability of…
Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed compare-and-contrast of the latest proposals to understand what…
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…
Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and…
Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test…
Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…
Backdoor attacks on text classifiers can cause them to predict a predefined label when a particular "trigger" is present. Prior attacks often rely on triggers that are ungrammatical or otherwise unusual, leading to conspicuous attacks. As a…