Related papers: Towards Million-Scale Adversarial Robustness Evalu…

The robustness of modern machine learning (ML) models has become an increasing concern within the community. The ability to subvert a model into making errant predictions using seemingly inconsequential changes to input is startling, as is…

We present a new algorithm to train a robust malware detector. Modern malware detectors rely on machine learning algorithms. Now, the adversarial objective is to devise alterations to the malware code to decrease the chance of being…

Deep neural networks have demonstrated remarkable effectiveness across a wide range of tasks such as semantic segmentation. Nevertheless, these networks are vulnerable to adversarial attacks that add imperceptible perturbations to the input…

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate…

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models. However, mainstream evaluation criteria experience limitations, even yielding discrepancies among results under different…

Network and system security are incredibly critical issues now. Due to the rapid proliferation of malware, traditional analysis methods struggle with enormous samples. In this paper, we propose four easy-to-extract and small-scale features,…

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard framework, which views robustness of predictions through a…

The success of multimodal data fusion in deep learning appears to be attributed to the use of complementary in-formation between multiple input data. Compared to their predictive performance, relatively less attention has been devoted to…

Machine learning (ML) is a rapidly developing area of medicine that uses significant resources to apply computer science and statistics to medical issues. ML's proponents laud its capacity to handle vast, complicated, and erratic medical…

Adversarial attacks on Face Recognition (FR) systems have demonstrated significant effectiveness against standalone FR models. However, their practicality diminishes in complete FR systems that incorporate Face Anti-Spoofing (FAS) models,…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

The deep neural network has attained significant efficiency in image recognition. However, it has vulnerable recognition robustness under extensive data uncertainty in practical applications. The uncertainty is attributed to the inevitable…

Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison to extensively studied single-task models, the adversarial…

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…