Related papers: Backdoor defense, learnability and obfuscation
This paper studies a strategic security problem in networked control systems under stealthy false data injection attacks. The security problem is modeled as a bilateral cognitive security game between a defender and an adversary, each…
We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition.…
Federated Learning (FL) enables numerous participants to train deep learning models collaboratively without exposing their personal, potentially sensitive data, making it a promising solution for data privacy in collaborative training. The…
Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…
Deep neural networks are learning models having achieved state of the art performance in many fields like prediction, computer vision, language processing and so on. However, it has been shown that certain inputs exist which would not trick…
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…
Interest in poisoning attacks and backdoors recently resurfaced for Deep Learning (DL) applications. Several successful defense mechanisms have been recently proposed for Convolutional Neural Networks (CNNs), for example in the context of…
Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. However, in certain scenarios, people may not…
The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these…
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…
As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed…
We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…
Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing stealthy backdoor…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…
A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…