相关论文: A Closer Look at Evaluating the Bit-Flip Attack Ag…

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with…

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well studied, Bit-Flip Attacks (BFAs) --…

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…

Adversarial attacks on Neural Network weights, such as the progressive bit-flip attack (PBFA), can cause a catastrophic degradation in accuracy by flipping a very small number of bits. Furthermore, PBFA can be conducted at run time on the…

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…

Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input. Most methods generate perturbations like normal noise, which is not…

This work presents CaFA, a system for Cost-aware Feasible Attacks for assessing the robustness of neural tabular classifiers against adversarial examples realizable in the problem space, while minimizing adversaries' effort. To this end,…

Deep neural networks (DNNs) have been shown to tolerate "brain damage": cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in a graceful degradation of classification accuracy. However,…

Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn…

We investigate the vulnerability of Graph Neural Networks (GNNs) to bit-flip attacks (BFAs) by introducing an analytical framework to study the influence of architectural features, graph properties, and their interaction. The expressivity…

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for convolutional neural…

Deep neural networks have been known to be vulnerable to adversarial examples, which are inputs that are modified slightly to fool the network into making incorrect predictions. This has led to a significant amount of research on evaluating…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that…

As Machine Learning (ML) applications rapidly grow, concerns about adversarial attacks compromising their reliability have gained significant attention. One unsupervised ML method known for its resilience to such attacks is Non-negative…

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite…

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…