相关论文: SEBA: Sample-Efficient Black-Box Attacks on Visual…

Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random…

Reinforcement learning (RL) has increasingly been applied to solve real-world planning problems, with progress in handling large state spaces and time horizons. However, a key bottleneck in many domains is that RL methods cannot accommodate…

With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…

Deep neural networks are susceptible to adversarial inputs and various methods have been proposed to defend these models against adversarial attacks under different perturbation models. The robustness of models to adversarial attacks has…

Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained…

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these…

The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely…

Modern AI systems increasingly comprise multiple interconnected neural networks to tackle complex inference tasks. Testing such systems for robustness and safety entails significant challenges. Current state-of-the-art robustness testing…

Vision-Language-Action (VLA) models have emerged as promising solutions for robotic manipulation, yet their robustness to real-world physical variations remains critically underexplored. To bridge this gap, we propose Eva-VLA, the first…

It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks without any…

In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our…

The security of AI-generated content (AIGC) detection is crucial for ensuring multimedia content credibility. To enhance detector security, research on adversarial attacks has become essential. However, most existing adversarial attacks…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

Despite their impressive performance, deep visual models are susceptible to transferable black-box adversarial attacks. Principally, these attacks craft perturbations in a target model-agnostic manner. However, surprisingly, we find that…

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary…

Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…

Deep learning has been broadly leveraged by major cloud providers, such as Google, AWS and Baidu, to offer various computer vision related services including image classification, object identification, illegal image detection, etc. While…