Related papers: Towards Reverse-Engineering Black-Box Neural Netwo…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their…

Using AI to create autonomous researchers has the potential to accelerate scientific discovery. A prerequisite for this vision is understanding how well an AI model can identify the underlying structure of a black-box system from its…

This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples by a substitute (source) model and utilize them to attack an unseen target model,…

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted…

Deep neural networks are powerful machine learning approaches that have exhibited excellent results on many classification tasks. However, they are considered as black boxes and some of their properties remain to be formalized. In the…

Recent researches have shown that machine learning based malware detection algorithms are very vulnerable under the attacks of adversarial examples. These works mainly focused on the detection algorithms which use features with fixed…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

As cloud computing becomes pervasive, deep learning models are deployed on cloud servers and then provided as APIs to end users. However, black-box adversarial attacks can fool image classification models without access to model structure…

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of…

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the…

A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs…

Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks. As the deployment of artificial…