Related papers: Dynamic Robustness Verification Against Weak Memor…
Numerous studies have established the necessity for developing safety equipment to detect drowsiness among vehicle drivers. However, for reliable implementations, such systems must employ dependable sources of stimuli; through…
With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the reliability of these…
The problem of quickest detection of a change in the distribution of a sequence of random variables is studied. The objective is to detect the change with the minimum possible delay, subject to constraints on the rate of false alarms and…
In safety-critical deep learning applications, robustness measures the ability of neural models that handle imperceptible perturbations in input data, which may lead to potential safety hazards. Existing pre-deployment robustness assessment…
Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…
Malware detection using Hardware Performance Counters (HPCs) offers a promising, low-overhead approach for monitoring program behavior. However, a fundamental architectural constraint, that only a limited number of hardware events can be…
As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have been conducted to improve its robustness against adversarial attacks.…
We present simple low-level conditions for identification in regression discontinuity designs using a potential outcome framework for the manipulation of the running variable. Using this framework, we replace the existing identification…
Keypoint detection underpins many vision tasks, including pose estimation, viewpoint recovery, and 3D reconstruction, yet modern neural models remain vulnerable to small input perturbations. Despite its importance, formal robustness…
Time-series anomaly detection is critical for ensuring safety in high-stakes applications, where robustness is a fundamental requirement rather than a mere performance metric. Addressing the vulnerability of these systems to adversarial…
Estimating dense correspondences between images is a long-standing image under-standing task. Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.…
Vehicle detection in real-time scenarios is challenging because of the time constraints and the presence of multiple types of vehicles with different speeds, shapes, structures, etc. This paper presents a new method relied on generating a…
As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks. However, ACL needs…
Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for tasks where complex policies are learned within reactive systems. Unfortunately, these policies are known to be susceptible to bugs. Despite significant…
This paper presents an application of specification based runtime verification techniques to control mobile robots in a reactive manner. In our case study, we develop a layered control architecture where runtime monitors constructed from…
Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory forecasting, some significant issues remain unaddressed. In…
Power is a RISC architecture developed by IBM, Freescale, and several other companies and implemented in a series of POWER processors. The architecture features a relaxed memory model providing very weak guarantees with respect to the…
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…
Robustness against noisy imaging is crucial for practical image anomaly detection systems. This study introduces a Robust Anomaly Detection (RAD) dataset with free views, uneven illuminations, and blurry collections to systematically…