Related papers: Adversarial Gain
In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and…
Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…
Deep learning models suffer from a phenomenon called adversarial attacks: we can apply minor changes to the model input to fool a classifier for a particular example. The literature mostly considers adversarial attacks on models with images…
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an…
Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine…
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that…
We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on…
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied…
Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical…
Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions. While research on the topic has mainly been focusing on the image domain, numerous industrial applications, in…
Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled around the underlying decision boundary. While this observation…
Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…
Adversarial examples are a type of attack on machine learning (ML) systems which cause misclassification of inputs. Achieving robustness against adversarial examples is crucial to apply ML in the real world. While most prior work on…
Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make…
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to…
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…
Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…
In spite of the successful application in many fields, machine learning models today suffer from notorious problems like vulnerability to adversarial examples. Beyond falling into the cat-and-mouse game between adversarial attack and…
We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image, our method operates on an entire concept - represented by…
It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the fact that neural…