Related papers: Adversary Model: Adaptive Chosen Ciphertext Attack…

A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

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…

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…

Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples…

Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as DALL-E, Stable Diffusion, Imagen, etc. In practice, it has…

Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically…

This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to…

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

Trajectory prediction is an integral component of modern autonomous systems as it allows for envisioning future intentions of nearby moving agents. Due to the lack of other agents' dynamics and control policies, deep neural network (DNN)…

Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to downstream-agnostic attacks (DAAs). Existing DAA methods operate under a permissive…

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial attack methodologies exhibit limited transferability and are…

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success in solving them. Despite their success, little is known about their robustness to adversarial attacks. In…

Adversarial attacks are major threats to the deployment of machine learning (ML) models in many applications. Testing ML models against such attacks is becoming an essential step for evaluating and improving ML models. In this paper, we…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…