Related papers: The Adaptive Arms Race: Redefining Robustness in A…

Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and…

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

Recent developments in adversarial machine learning have highlighted the importance of building robust AI systems to protect against increasingly sophisticated attacks. While frameworks like AI Guardian are designed to defend against these…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

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…

We study dynamic algorithms robust to adaptive input generated from sources with bounded capabilities, such as sparsity or limited interaction. For example, we consider robust linear algebraic algorithms when the updates to the input are…

Robots have limited adaptation ability compared to humans and animals in the case of damage. However, robot damages are prevalent in real-world applications, especially for robots deployed in extreme environments. The fragility of robots…

As AI advances, broader consensus is needed to determine research priorities. This endeavor discusses offensive AI and provides guidance by leveraging Sustainable Development Goals (SDGs) and interpretability techniques. The objective is to…

Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease…

Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. In this paper, we examine the robustness of state-of-the-art action recognizers…

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust…

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Recently, large pre-trained foundation models have become widely adopted by machine learning practitioners for a multitude of tasks. Given that such models are publicly available, relying on their use as backbone models for downstream tasks…

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few…

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

Cyber-attacks can occur at machine speeds that are far too fast for human-in-the-loop (or sometimes on-the-loop) decision making to be a viable option. Although human inputs are still important, a defensive Artificial Intelligence (AI)…

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…

As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged. Despite notable progress, the performance of…

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…