Related papers: Efficient Certified Defenses Against Patch Attacks…

Learning-based autonomous driving systems remain critically vulnerable to adversarial patches, posing serious safety and security risks in their real-world deployment. Black-box attacks, notable for their high attack success rate without…

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Synthetic image generation has opened up new opportunities but has also created threats in regard to privacy, authenticity, and security. Detecting fake images is of paramount importance to prevent illegal activities, and previous research…

In the context of test case based automated program repair (APR), the research community call the patches that pass all the test cases but fail to actually fix the bug test case overfitted patches. Currently, overfitted patches has to be…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

As deep learning models continue to advance and are increasingly utilized in real-world systems, the issue of robustness remains a major challenge. Existing certified training methods produce models that achieve high provable robustness…

Multi-sensor fusion systems (MSFs) play a vital role as the perception module in modern autonomous vehicles (AVs). Therefore, ensuring their robustness against common and realistic adversarial semantic transformations, such as rotation and…

To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds for a small but…

Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturbances and uncertainty. We present a method for jointly…

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose significant threats to the reliability and safety of these systems, with physical…

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…

Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found deep neural networks vulnerable to adversarial examples. Since…

Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an…

Object detection plays a crucial role in many security-sensitive applications. However, several recent studies have shown that object detectors can be easily fooled by physically realizable attacks, \eg, adversarial patches and recent…

Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks against 3D PC classifiers are all test-time evasion (TTE) attacks…

Adversarial robustness of deep models is pivotal in ensuring safe deployment in real world settings, but most modern defenses have narrow scope and expensive costs. In this paper, we propose a self-supervised method to detect adversarial…

Development of defenses against physical world attacks such as adversarial patches is gaining traction within the research community. We contribute to the field of adversarial patch detection by introducing an uncertainty-based adversarial…